ClawAudit verdict
youmind-wechat-article
WeChat publishing skill via YouMind connector with explicit disclosure of credential handling and no hidden 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.
Findings (8)
Possible hardcoded credential
references/youmind-integration.md · code · api_key: "sk-ym-xxxxxxxxxxxxxxxxxxxx
Pipe to python — executes piped content as Python code
references/resilience.md · prose · downgraded · | Python
<script> tag in markdown — potential code injection
references/wechat-constraints.md · prose · downgraded · <script>
Instructs covert action — may act without user awareness
references/writing-guide.md · prose · downgraded · Quietly
Dynamic import() — loads module at runtime
toolkit/src/cli.ts · prose · downgraded · import('
References child_process — can spawn system processes
toolkit/src/mermaid-processor.ts · prose · downgraded · child_process
Uses exec() — may execute shell commands
toolkit/src/theme-engine.ts · prose · downgraded · exec(
Popular HTTP library — network access
toolkit/package.json · prose · downgraded · node-fetch
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
Requires 1 environment variable. (1 sensitive: YOUMIND_API_KEY).
Is this flag fair?
Thanks — recorded.