ClawAudit verdict

hermes-agent-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Provides install/initialisation commands for a legitimate memory/skill system; no concrete malicious code is present.

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

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

45
security
90
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match high

Pipe to python — executes piped content as Python code

references/VERSION_MANAGEMENT.md · prose · downgraded · | Python

Pattern match medium

References agent memory files

references/DEPLOYMENT_GUIDE.md · code · MEMORY.md

Pattern match medium

Sets world-executable permissions

references/DEPLOYMENT_GUIDE.md · code · chmod 755

Pattern match medium

Python shutil file operation — copies/moves/deletes files

references/TEST_GUIDE.md · code · shutil.rmtree(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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.

package_install

Is this flag fair?

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