Caveat verdict
amath_skill
amath-skill
The skill executes an external script which could potentially be risky, but the purpose seems legitimate.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
OPENCLAW_SETUP.md · code · curl -fsSL https://openclaw.ai/install.sh | bash
Pipe to bash — executes piped content as shell commands
OPENCLAW_SETUP.md · code · | bash
Accesses OpenClaw config/secrets directly
OPENCLAW_SETUP.md · prose · downgraded · ~/.openclaw/openclaw.json
HTTP request to bare IP address — common in malicious payloads
OPENCLAW_SETUP.md · prose · downgraded · http://127.0.0.1
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/F). 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.
credential_access Is this flag fair?
Thanks — recorded.