ClawAudit verdict
nanda-chapter
The skill uses its capabilities for a legitimate and transparent purpose of registering with a NANDA chapter and handling intents.
⚠ 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 (4)
Prompt injection — tries to override agent instructions
helpers/_sanitize.py · prose · downgraded · ignore prior
instructions
Instructs covert action — may act without user awareness
helpers/discover_chapter.py · prose · downgraded · silently
Python os.environ.get — reads environment variable
helpers/discover_chapter.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
helpers/sign_request.py · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
network_indata_encoding Is this flag fair?
Thanks — recorded.