Caveat verdict
runtime-sentinel
Runtime security guardian skill that provides skill integrity hashing, injection detection, and credential auditing via a local Rust binary; premium features use x402 USDC micropayments on Base, all behavior is defensive and transparent.
⚠ 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.
Permission integrity
package_install
Findings (7)
References sudo — requests elevated privileges
README.md · code · sudo
Writes to SKILL.md — self-modifying skill
references/threat-model.md · prose · downgraded · SKILL.md after install; skills that append
Prompt injection — tries to override agent instructions
references/threat-model.md · prose · downgraded · ignore previous instructions
Accesses .ssh directory
references/threat-model.md · prose · downgraded · .ssh/
Instructs covert action — may act without user awareness
references/threat-model.md · prose · downgraded · silently
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Base64 encoding/decoding
references/threat-model.md · prose · downgraded · Base64-encode
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.