Caveat verdict
self-improving-agent
haiqing-self-improving-agent
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill provides an AI self-improving agent that learns from mistakes, corrections, and successes, and installs packages, but does not exhibit any clearly malicious behavior.
⚠ 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.
75
security
90
transparency
90
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Findings (1)
Pattern match high
References sudo — requests elevated privileges
SKILL.md · code · sudo
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.