ClawAudit verdict

hetu-lyrics-blessing

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

Fetches song lyrics from Baidu Baike via browser automation and sends them via SMTP email; all network activity is to explicitly stated destinations (baike.baidu.com and user-configured SMTP server) and the executionSinkDetected is the npm install step.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
40
transparency
70
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md ยท code ยท PASSWORD = "your_auth_code

Pattern match medium

subprocess execution โ€” runs system commands from Python

scripts/send_lyrics.py ยท prose ยท downgraded ยท subprocess.run(

Pattern match medium

subprocess with shell=True โ€” command injection vector

scripts/send_lyrics.py ยท prose ยท downgraded ยท subprocess.run(cmd, shell=True

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution โ€” cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

package_installnetwork_infile_write

Is this flag fair?

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