Caveat verdict

agentic-loop-upgrade

agent-mode-upgrades

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

Enhances agentic loop capabilities with secure design and no evidence of malicious intent.

⚠ 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.

25
security
90
transparency
70
maintenance

Findings (7)

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Pattern match high

Pipe to sh — executes piped content as shell commands

src/dist/execution/approval-gate.js · prose · downgraded · |sh

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

References agent configuration files

references/confidence-gates.md · code · AgentConfig

Pattern match medium

apt-get install — installs system packages

src/execution/retry-engine.ts · prose · downgraded · apt-get install

Pattern match low

Accesses sensitive environment variables

scripts/verify.sh · prose · downgraded · process.env.OPENCLAW_TOKEN

Pattern match low

Popular HTTP library — network access

scripts/verify.sh · prose · downgraded · axios

Why the tier is capped

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

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