ClawAudit verdict

listing-swarm

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

AI directory submission automation skill using BYOK captcha and IMAP credentials; explicitly contains no embedded credentials, all keys are user-provided at runtime, and data flows only to target submission forms.

⚠ 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.

35
security
100
transparency
90
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-own-2captcha-key

Pattern match high

Uses eval() — can execute arbitrary code

SECURITY.md · prose · downgraded · eval(

Pattern match medium

Dynamic import() — loads module at runtime

captcha.js · prose · downgraded · import('

Pattern match low

Accesses sensitive environment variables

captcha.js · prose · downgraded · process.env.CAPTCHA_API_KEY

Pattern match low

Popular HTTP library — network access

captcha.js · prose · downgraded · node-fetch

Permissions & capabilities

Requires 5 environment variables. (2 sensitive: CAPTCHA_API_KEY, IMAP_PASSWORD). Requires 1 system binary.

Is this flag fair?

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