ClawAudit verdict
openclaw-weixin
The skill installs a package, which may pose a risk if not properly validated.
⚠ 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
package_install
Findings (6)
Base64 encoding/decoding
README.md · code · base64-encode
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Dynamic import() — loads module at runtime
src/auth/accounts.ts · prose · downgraded · import("
References child_process — can spawn system processes
src/log-upload.ts · prose · downgraded · child_process
Accesses sensitive environment variables
src/auth/pairing.ts · prose · downgraded · process.env.OPENCLAW_OAUTH
Popular HTTP library — network access
src/cdn/pic-decrypt.ts · prose · downgraded · got
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 system binary.
package_install Is this flag fair?
Thanks — recorded.