ClawAudit verdict
voice-ai-integration
Integration guide for Shengwang RTC/RTM/ConvoAI products; routes user requests to appropriate documented modules and provides API call templates with no credential harvesting or malicious patterns.
⚠ 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)
Possible hardcoded credential
references/general/credentials-and-auth.md · code · token="007abcxxxxxxx123
Pipe to python — executes piped content as Python code
references/conversational-ai/quickstart.md · prose · downgraded · | Python
Instructs covert action — may act without user awareness
references/conversational-ai/sample-repos.md · prose · downgraded · silently
Popular HTTP library — network access
references/conversational-ai/common-errors.md · code · Got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
Is this flag fair?
Thanks — recorded.