Skills/PyPI/stratum-mcp

stratum-mcp@0.2.114

CAUTION· not started

Publisher claims: "Stratum MCP server for Claude Code — structured execution, typed contracts, postcondition enforcement" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher smartmemory · publishing for 268 daysInstalls 479Last detonated 5 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
STRATUM_GUARD_OVERRIDE_TOKENConfiguration, not credentials: CLAUDE_MODEL, STRATUM_CODEX_ALLOW_WRITE, STRATUM_CODEX_STREAM_LIMIT_BYTES, STRATUM_DEFAULT_AGENT, STRATUM_GUARD_ALLOW_COMMANDS, STRATUM_GUARD_CMD_TIMEOUT_S
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for STRATUM_GUARD_OVERRIDE_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx stratum-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-19 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python exec or eval of computed codesrc/stratum_mcp/executor.py:391 · Python exec or eval of computed codereturn eval(code, {"__builtins__": {}, **_ENSURE_BUILTINS}, {bind: value})Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/spec.py:861 · Python subprocess execution detecteddiff_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codesrc/stratum_mcp/executor.py:449 · Python exec or eval of computed codereturn bool(eval(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:97 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-onboard/SKILL.md:169 · Instructs the agent to modify its persistent memory or instruction files…rns. **After `stratum_audit`:** The `write_memory` step produces the entries — write them to `.claude/memory/MEMORY.md` (create directory and file if missing). Tag each entry with the skill it appli…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-debug/SKILL.md:198 · Instructs the agent to modify its persistent memory or instruction files**After the fix:** Append to `MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:43 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-onboard/SKILL.md:22 · Instructs the agent to modify its persistent memory or instruction files5. Write conclusions to `MEMORY.md` at `.claude/memory/MEMORY.md` (create if missing)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-migrate/SKILL.md:151 · Instructs the agent to modify its persistent memory or instruction files**After migration:** Append to `MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-review/SKILL.md:179 · Instructs the agent to modify its persistent memory or instruction files…ule with known fragility, a class of issue this project tends to have)? If yes, append a one-liner to `MEMORY.md`: ``` [stratum-review] <pattern> — e.g. "auth middleware bypasses rate limitin…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-onboard/SKILL.md:3 · Instructs the agent to modify its persistent memory or instruction files--- name: stratum-onboard description: Read a codebase cold and write a project-specific MEMORY.md from scratch — architecture patterns, test conventions, module constraints, kno…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/guard/evidence.py:127 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codesrc/stratum_mcp/executor.py:352 · Python exec or eval of computed codevalue = eval(code, {"__builtins__": {}, **_ENSURE_BUILTINS}, {"result": result})Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:75 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/spec.py:869 · Python subprocess execution detecteduntracked_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/provenance_crawl.py:36 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-speckit/SKILL.md:287 · Instructs the agent to modify its persistent memory or instruction files**After Phase 4 `stratum_audit`:** For each step with `attempts > 1`, ask: does the retry reveal a project-specific pattern worth capturing? Append one-liners to `MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-test/SKILL.md:144 · Instructs the agent to modify its persistent memory or instruction files**After `stratum_audit`:** If any step needed retries, append to `MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python exec or eval of computed codesrc/stratum_mcp/executor.py:679 · Python exec or eval of computed codereturn bool(eval(code, {"__builtins__": {}, "None": None, "True": True, "False": False,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-refactor/SKILL.md:158 · Instructs the agent to modify its persistent memory or instruction files**After each extraction:** If a step needed retries because of an unexpected dependency or import constraint, append to `MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/skills/stratum-feature/SKILL.md:218 · Instructs the agent to modify its persistent memory or instruction files…ious coupling, a test convention, an invariant that must be preserved)? If yes, append a one-liner to `MEMORY.md`: ``` [stratum-feature] tests use factory_boy fixtures, not pytest fixtures — …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:104 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/proc_identity.py:111 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/guard/evidence.py:153 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:132 · Python subprocess execution detectedres = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codesrc/stratum_mcp/executor.py:301 · Python exec or eval of computed codereturn bool(eval(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Destructive file system command detectedtests/test_guard_evidence.py:38 · Destructive file system command detectedev.parse_predicate_statement("os_system('rm -rf /')")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/executor.py:1090 · Process kill command — agent can terminate processes# v0.2: terminal status — set to "killed" when gate kill fires with null on_killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/hooks/stratum-session-stop.sh:2 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file# Stratum hook (T2-M3): append a timestamped summary note to MEMORY.md atFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:26 · Python subprocess execution detectedsubprocess.run(["git", "commit", "-qm", "init"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/server.py:389 · Process kill command — agent can terminate processes# Graceful shutdown of THIS controller: kill only the writers it owns.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_guard_evidence.py:92 · Python subprocess execution detectedsubprocess.run(["git", *args], cwd=tmp_path, capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:85 · Python subprocess execution detectedsubprocess.run(["git", "add", filename], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/result_cache.py:57 · Process kill command — agent can terminate processes"""True when the kill switch env var is set to a truthy value."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_goal_tool.py:23 · Process kill command — agent can terminate processes- kill maps to killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/parallel_exec.py:994 · Process kill command — agent can terminate processes# cancel of a reparentable task, do NOT interrupt (would killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_goal_e2e.py:1154 · Process kill command — agent can terminate processesprompt="status kill test",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_t2f5_executor.py:221 · Process kill command — agent can terminate processes# detach-don't-kill (review #1)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/server.py:395 · Process kill command — agent can terminate processes# run with no ownership stamp, never kill it while its child is alive.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:81 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q", "-b", "main"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/executor.py:101 · Process kill command — agent can terminate processes# Timeout — hard kill the subprocessFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_goal_e2e.py:1166 · Process kill command — agent can terminate processes# After kill the goal state and flow may be cleaned up; if decision_gates isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:25 · Python subprocess execution detectedsubprocess.run(["git", "add", "README"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/executor.py:80 · Process kill command — agent can terminate processes"""Run a regex search in a subprocess with a hard kill timeout.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:21 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_codex_durable.py:6 · Process kill command — agent can terminate processesprocess-group interrupt, and the "finally must not kill the detached child"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:83 · Python subprocess execution detectedsubprocess.run(["git", "config", "user.name", "Test"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_goal_e2e.py:1133 · Process kill command — agent can terminate processes"""kill → status surface shows decision='kill', outcome='kill'."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:152 · Python subprocess execution detectedsubprocess.run(["git", "add", ".gitignore"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/parallel_exec.py:1103 · Process kill command — agent can terminate processes# T2-F5-RESUME (review #1): detach-don't-kill — bypass the WHOLEFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:153 · Python subprocess execution detectedsubprocess.run(["git", "commit", "-q", "-m", "ignore"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/server.py:2649 · Process kill command — agent can terminate processes"kill routes to on_kill target (or terminates the flow if null). "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:70 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file| `/stratum-onboard` | Read a new codebase cold and write project-specific `MEMORY.md` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandtests/test_reattach.py:300 · Process kill command — agent can terminate processes"""A successful completion under require=all does NOT cascade-kill siblings."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:23 · Python subprocess execution detectedsubprocess.run(["git", "config", "user.name", "t"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:95 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file| `/stratum-onboard` | Read a new codebase cold and write project-specific `MEMORY.md` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/stratum_mcp/parallel_exec.py:1370 · Process kill command — agent can terminate processes# and kill the sibling reparented children so their readers terminalize.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/stratum_mcp/server.py:4524 · File permission modification command — agent changes file ownership/permissions# Neutral wording covers install, update, and re-chmod casesFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_codex_durable.py:248 · Process kill command — agent can terminate processes# interrupt (killpg) + finally-no-kill teardown contractFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/stratum_mcp/worktree.py:196 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:22 · Python subprocess execution detectedsubprocess.run(["git", "config", "user.email", "t@t"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/server.py:2759 · Process kill command — agent can terminate processes"as an explicit kill outcome. "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_codex_durable.py:279 · Process kill command — agent can terminate processes# closing the generator (shutdown/cancel) must NOT kill the detached childFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/connectors/codex.py:807 · Process kill command — agent can terminate processesstill reparentable. The ``finally`` does NOT kill the child — only anFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/parallel_exec.py:1092 · Process kill command — agent can terminate processes# shutdown — leave it `running` and don't kill the durable child.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_goal_e2e.py:1121 · Process kill command — agent can terminate processes"Finding 2a: confirm→approve, reject→revise, kill→kill mapping required."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:82 · Python subprocess execution detectedsubprocess.run(["git", "config", "user.email", "[email protected]"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_worktree.py:86 · Python subprocess execution detectedsubprocess.run(["git", "commit", "-q", "-m", "init"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_guard_evidence.py:99 · Python subprocess execution detectedsha = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/stratum_mcp/server.py:4386 · File permission modification command — agent changes file ownership/permissions# Content matches but execute bit dropped — re-chmod onlyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/server.py:2758 · Process kill command — agent can terminate processes"fires an auto-kill with resolved_by: system following the same on_kill routing "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agent_run_bg.py:286 · Python subprocess execution detecteddead = subprocess.Popen(["true"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/executor.py:2296 · Process kill command — agent can terminate processes"killed" — flow terminated (kill with null on_kill)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_goal_tool.py:493 · Process kill command — agent can terminate processes"""D3: kill → outcome=kill."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_guard_evidence.py:38 · Destructive command against a filesystem root or deviceev.parse_predicate_statement("os_system('rm -rf /')")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stratum_mcp/executor.py:45 · Process kill command — agent can terminate processesUses multiprocessing to enforce hard kill on stuck regex workers.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/server.py:4804 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileremoved.append("CLAUDE.md")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/server.py:4692 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filechanged.append("CLAUDE.md")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/server.py:4688 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filechanged.append("CLAUDE.md")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/stratum_mcp/server.py:4624 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Write .claude/mcp.json and append Stratum block to CLAUDE.md."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈14,705 tok
9 files · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for stratum-mcp@0.2.114 as of 4 h ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim smartmemory: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim smartmemoryPropose a patch to the maintainer