ClawAudit verdict
code-mirror
Despite network capabilities listed, the skill only reads local project files to detect stack types and generates counterpart code — no evidence of data exfiltration or misuse of network access in the content.
⚠ 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
network_out
Findings (4)
Pipe to python — executes piped content as Python code
SKILL.md · code · | Python
Popular HTTP library — network access
SKILL.md · code · axios
axios HTTP request
SKILL.md · code
fetch() — outbound network request
SKILL.md · code
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessnetwork_in Is this flag fair?
Thanks — recorded.