Skills/PyPI/claude-archive-mcp

claude-archive-mcp@1.14.0

CAUTION

Publisher claims: "Local stdio MCP server exposing unified Claude chat history (claude.ai export + Claude Code sessions) as ranked, scoped, structured search." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher manderse-dispatch · joined 5 days agoInstalls 276Last detonated 5d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-29 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive command against a filesystem root or device; Outbound HTTP to raw IP address. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/claude-archive-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/claude-archive-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only

Static findings

HIGH
Destructive file system command detectedscripts/j7_hostile_probe.py:54 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/j7_hostile_probe.py:54 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Outbound HTTP to raw IP addressscripts/container_controls.py:1236 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/container_controls.py:315 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/container_controls.py:294 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/h9_score.py:261 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/gateway_proof.py:242 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/reindex_embed.py:30 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/h4_measure.py:326 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/gateway_proof.py:376 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/gateway_proof.py:103 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rh_scale_row.py:547 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/continuity_status.py:9 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/container_controls.py:326 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/sidecar_backfill.py:368 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/gateway_proof.py:388 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/rd11_rrf_probe.py:16 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/gateway_proof.py:395 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/re06_rrf_reprobe.py:7 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL using raw IP addressscripts/container_controls.py:1236 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/container_controls.py:369 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rh_scale_row.py:478 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/gateway_proof.py:246 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/benchmarks/_common.py:283 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/premise_check.py:275 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/container_controls.py:308 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/update_chats.py:421 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/upgrade_drill.py:223 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim manderse-dispatch: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim manderse-dispatch