ClawAudit verdict
topic-research
The skill runs deep research via the Tavily CLI on user-specified topics and saves results to local markdown files within the project; it uses the documented tvly CLI tool and writes output locally, with executionSinkDetected referring only to the legitimate documented CLI invocation.
⚠ 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 (3)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
README.md · code · curl -fsSL https://cli.tavily.com/install.sh | bash
Pipe to bash — executes piped content as shell commands
README.md · code · | bash
subprocess execution — runs system commands from Python
runtime.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). 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.