Caveat verdict

clamav

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

The skill appears to provide reference implementations for ClamAV, an open-source antivirus tool. It seems to operate within legitimate system administration or security operations.

⚠ 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.

43
security
100
transparency
90
maintenance

Findings (7)

Pattern match high

Uses eval() — can execute arbitrary code

scripts/script.sh · prose · downgraded · eval(

Pattern match medium

yum install — installs system packages

scripts/script.sh · prose · downgraded · yum install

Pattern match medium

References sudo — requests elevated privileges

scripts/script.sh · prose · downgraded · sudo

Pattern match medium

Instructs covert action — may act without user awareness

scripts/script.sh · prose · downgraded · silently

Pattern match low

Changes file ownership

scripts/script.sh · prose · downgraded · chown

Pattern match low

Base64 encoding/decoding

scripts/script.sh · prose · downgraded · base64_decode

Pattern match low

Sets world-executable permissions

scripts/script.sh · prose · downgraded · chmod 700

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