Skills/npm/anti-slop-engineering

anti-slop-engineering@1.13.0

CAUTION· startup only

Publisher claims: "An Engineering Discipline Playbook, Agent Skill & Triage Guard for AI Coding Agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher immamdouhaboammar · publishing for 167 daysInstalls 3,626Last detonated 14 min ago

Coverage

Startup only; authenticated tool behavior not tested.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What changed since 1.8.0

vet-skills diff anti-slop-engineering 1.8.0 1.13.0

This version reaches for something 1.8.0 did not: 4 new hosts (bun.sh, golang.org, nodejs.org, rustup.rs). Compared from the two recorded runs, not from source.

New hosts
bun.sh, golang.org, nodejs.org, rustup.rs

1.13.0 was run further than 1.8.0 (startup only vs install only); some additions may be first observations rather than changes.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-22 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 21 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
20sprocessexec /app/apps/web/node_modules/.bin/git
20sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/git
20sprocessexec /app/node_modules/.bin/git
20sprocessexec /pnpm/git
20sprocessexec /usr/local/sbin/git
20sprocessexec /usr/local/bin/git
20sprocessexec /usr/sbin/git
20sprocessexec /usr/bin/git
20sclaimedstartup only: exited (0) before answering · (node:2204) [UNDICI-EHPA] Warning: EnvHttpProxyAgent is experimental, expect them to change at any time. (Use `node --trace-warnings ...` to show where the warning was created) ERROR: fatal: not a git repository (or any of the parent directories): .git
20sprocessscript backend runs setup only
20sprocesssecond launch, clock +45 days, CI unset

Static findings

MEDIUM
Python subprocess execution detectedscripts/bump_version.py:218 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/exec_guard.py:229 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn any(name == ".env" or name.startswith(".env.") for name in names)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/bump_version.py:319 · Python subprocess execution detectedproc = subprocess.run(command, capture_output=True, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/forensic_hunter.py:414 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"(?i)(?:process\.env\.[A-Z0-9_]+|os\.getenv\([^)]+\))\s*(?:\|\||\?\?|,)\s*['\"](?:secret|password|admin|default|changeme|123456|dev)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/attention_guard.py:485 · Python subprocess execution detectedproc = subprocess.run(["git", "diff", base_id, "--"], cwd=repo_root, capture_output=True, text=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 detectedscripts/comment_budget_guard.py:260 · 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 detectedscripts/audit_runner.py:732 · Python subprocess execution detectedreturn subprocess.run([options.make, *targets]).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/benchmark_static_guards.py:35 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/audit_runner.py:788 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=GUARD_TIMEOUT_SECONDS, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/extract_skill_rules.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file_patterns": ["*.env*", "src/security/**", "src/crypto/**", "**/auth/**"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/audit_runner.py:697 · Python subprocess execution detectedresult = subprocess.run(["git", *args], cwd=root, check=True, stdout=subprocess.PIPE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/audit_runner.py:684 · Python subprocess execution detectedres = subprocess.run(command, cwd=cwd)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationscripts/styleseed_guard.py:762 · Credential pass-through configuration — agent relays sensitive credentialspassFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedscripts/build_plugin_release.py:73 · 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 detectedscripts/demock_guard.py:79 · 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 subprocess execution detectedscripts/repository_evidence.py:50 · Python subprocess execution detectedreturn subprocess.run(command, capture_output=True, check=check, env=env, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/skills_compliance_engine.py:183 · Python subprocess execution detectedres = subprocess.run(cmd, cwd=ROOT, capture_output=True, text=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 detectedscripts/tagore_guard.py:682 · Python subprocess execution detectedres = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=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 detectedscripts/pr_boundary_guard.py:71 · 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 exec or eval of computed codescripts/mutation_fixture.py:41 · Python exec or eval of computed codeexec(program, globals_scope) # The program originates only from SOURCE above.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 detectedscripts/verification_oracle_guard.py:370 · 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 subprocess execution detectedscripts/verification_oracle_guard.py:576 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/mutation_fixture.py:49 · Python subprocess execution detectedwith subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/verification_oracle_guard.py:384 · 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 detectedscripts/invariant_steward_guard.py:422 · Python subprocess execution detectedname_proc = subprocess.run(["git", "diff", "--name-only", base_id, "--"], capture_output=True, text=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 detectedscripts/forensic_hunter.py:692 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=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 detectedscripts/invariant_steward_guard.py:420 · Python subprocess execution detectedproc = subprocess.run(["git", "diff", base_id, "--"], capture_output=True, text=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 detectedscripts/verification_oracle_guard.py:540 · Python subprocess execution detectedtree = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/property_test_guard.py:326 · Python subprocess execution detectedproc = subprocess.run(cmd_parts)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/verification_oracle_guard.py:434 · 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 detectedscripts/typescript_compiler_evidence.py:49 · Python subprocess execution detectedchild = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/root_fix_guard.py:150 · Python subprocess execution detectedresult = subprocess.run(["git", "-C", str(repo), *git_args], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:49 · npx invocation of non-well-known package — may execute untrusted code…erministic machine codes and remediation guidance. Audit contract records with `npx anti-slop-engineering contract audit <record.json> --json`. 23. **UI Craftsmanship, Copywriting & WCA…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/verification_oracle_guard.py:533 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/git_changeset.py:17 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/safe_install.py:65 · 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 detectedscripts/diff_lifecycle.py:53 · Python subprocess execution detectedprocess = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/verification_oracle_guard.py:711 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/verification_oracle_guard.py:709 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)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 filesscripts/validate_skills.py:271 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileerrors.append("AGENTS.md: missing repository instruction file")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:51 · npx invocation of non-well-known package — may execute untrusted code…ing tabindex for composite controls, and ARIA live regions. Audit records with `npx anti-slop-engineering apple-craft audit <record.json> --json`. 25. **Observability & SLO Architect (G…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:52 · npx invocation of non-well-known package — may execute untrusted code….4x 1h/5m for paging; 6.0x 6h/30m for ticketing). Audit telemetry records with `npx anti-slop-engineering observability audit <record.json> [--source <file>] --json`. 26. **Repo Memory …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandscripts/rollout_guard.py:299 · Process kill command — agent can terminate processes# 2. Hardcoded feature flags without kill switch or expirationFix: 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 filesbin/cli.js:619 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file2. Update SKILL.md & AGENTS.md with concise agent directivesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagebin/cli.js:227 · npx invocation of non-well-known package — may execute untrusted codenpx anti-slop-engineering [command] [options]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈10,134 tok
1 file · 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim immamdouhaboammar: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  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. 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.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim immamdouhaboammarPropose a patch to the maintainer