Caveat verdict

skill-publisher

agent-skill-publisher

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

This skill automates publishing agent skills but includes execution sink detection, suggesting potential risks if mishandled.

⚠ 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.

65
security
80
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (1)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf /

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_installagent_memory

Is this flag fair?

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