Caveat verdict

agi-evolution-model

agi-evolution-model-basic

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill implements an AGI evolution model, focusing on self-improvement through user interactions, without showing 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.

45
security
90
transparency
70
maintenance

Findings (4)

Pattern match critical

Pipe to python — executes piped content as Python code

references/intentionality_architecture.md · code · | python3

Pattern match high

Uses eval() — can execute arbitrary code

scripts/perception_node.py · prose · downgraded · eval(

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 755

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/metacognition_history.py · prose · downgraded · shutil.move(

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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