ClawAudit verdict
telnyx-rag
The skill is used for semantic search and Q&A over workspace files, and it doesn't exhibit any malicious or deceptive behavior.
⚠ 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
agent_memory
Findings (5)
Possible hardcoded credential
ask.py · prose · downgraded · API_KEY="):
return line.split(
References agent memory files
SKILL.md · code · MEMORY.md
Python urllib.request — network access
ask.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
ask.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
setup.sh · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). 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: TELNYX_API_KEY). Requires 1 system binary.
credential_accessagent_memory Is this flag fair?
Thanks — recorded.