Caveat verdict

multi-ai-search-analysis

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Multi-AI comparative analysis skill orchestrating browser-based queries to public AI platforms; browser automation for querying public web services is legitimate research tooling.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
50
transparency
70
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Findings (6)

Pattern match high

Pipe to python — executes piped content as Python code

COMPLETION_SUMMARY.md · prose · downgraded · | Python

Pattern match medium

subprocess execution — runs system commands from Python

scripts/install.py · prose · downgraded · subprocess.run(

Pattern match medium

subprocess with shell=True — command injection vector

scripts/install.py · prose · downgraded · subprocess.run(cmd, shell=True

Pattern match medium

os.system/popen — direct OS command execution

scripts/run.py · prose · downgraded · os.system(

Pattern match low

References agent memory files

IMPLEMENTATION_SUMMARY.md · prose · downgraded · MEMORY.md

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/test.py · prose · downgraded · shutil.rmtree(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

file_read

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API