Caveat verdict
content-security-filter
Prompt injection and malware detection filter scanning for attack patterns; executionSinkDetected reflects usage-docs example commands, and the skill is explicitly a defensive security tool.
⚠ 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.
Findings (4)
Prompt injection — tries to override agent instructions
SKILL.md · code · ignore all previous instructions
Pipe to python — executes piped content as Python code
scripts/content-security-filter.py · prose · downgraded · | python3
Pipe to bash — executes piped content as shell commands
scripts/content-security-filter.py · prose · downgraded · |bash
Python urllib.request — network access
scripts/content-security-filter.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.
Is this flag fair?
Thanks — recorded.