ClawAudit verdict

rice-phenotype-prediction

gain

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

All models and data are bundled with the skill; it runs inference locally and does not contact external services or expose secrets.

⚠ 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.

75
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match high

Uses eval() — can execute arbitrary code

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

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