ClawAudit verdict
zeelin-writing
zeelin-writing-v2
A writing assistant skill that stores API keys locally in a config file and uses them for WeChat/Google APIs; all credential handling is local and transparent with no evidence of exfiltration.
⚠ 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.
Permission integrity
agent_memory
Findings (4)
Possible hardcoded credential
scripts/初始化.sh · prose · downgraded · API_KEY: " API_KEY
if [ -n
References child_process — can spawn system processes
scripts/markdown-to-html.ts · prose · downgraded · child_process
Dynamic import() — loads module at runtime
scripts/markdown-to-html.ts · prose · downgraded · import('
Accesses shell history/config
scripts/初始化.sh · prose · downgraded · ~/.zshrc
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D/F). 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.
agent_memory Is this flag fair?
Thanks — recorded.