ClawAudit verdict

jcvd

jean-claw-van-damme

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

Authorization gatekeeper skill implementing the APOA security framework to enforce scoped, time-bound permissions for agent actions; the skill's purpose is explicitly defensive security monitoring and audit logging.

⚠ 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.

0
security
100
transparency
90
maintenance

Findings (13)

Pattern match high

Uses eval() — can execute arbitrary code

SKILL.md · prose · downgraded · eval(

Pattern match high

Prompt injection — tries to override agent instructions

SKILL.md · prose · downgraded · ignore previous instructions

Pattern match high

Accesses sensitive system files

scan-skill.sh · prose · downgraded · /etc/passwd

Pattern match medium

apt-get install — installs system packages

audit-export.sh · prose · downgraded · apt-get install

Pattern match medium

References SSH/GPG private keys

scan-skill.sh · prose · downgraded · SSH_KEY

Pattern match medium

Accesses system credential store

scan-skill.sh · prose · downgraded · keychain

Pattern match medium

References sudo — requests elevated privileges

scan-skill.sh · prose · downgraded · sudo

Pattern match medium

Uses exec() — may execute shell commands

scan-skill.sh · prose · downgraded · exec(

Pattern match medium

Dynamic import() — loads module at runtime

scan-skill.sh · prose · downgraded · import("

Pattern match low

References agent configuration files

policy.json · prose · downgraded · agent_config

Pattern match low

Sets world-executable permissions

scan-skill.sh · prose · downgraded · chmod 777

Pattern match low

Changes file ownership

scan-skill.sh · prose · downgraded · chown

Pattern match low

String.fromCharCode — can build strings to evade detection

scan-skill.sh · prose · downgraded · String.fromCharCode

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