ClawAudit verdict
zhy-article-illustrator
The skill illustrates a Markdown article with high-finish editorial visuals. It seems to be used for its stated purpose and does not involve any malicious behavior.
⚠ 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.
Findings (5)
References child_process — can spawn system processes
scripts/illustrate-article.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
scripts/illustrate-article.ts · prose · downgraded · spawn(
Uses exec() — may execute shell commands
scripts/illustrate-article.ts · prose · downgraded · exec(
Accesses sensitive environment variables
scripts/image-gen.ts · prose · downgraded · process.env.XIAOMI_API_KEY
Base64 encoding/decoding
scripts/image-gen.ts · prose · downgraded · Base64Encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.