Caveat verdict

agent-work-visibility

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

Task transparency layer that injects progress reporting protocols into SOUL.md/AGENTS.md; explicitly states no network requests or key reads, and process_exec is used for local activation scripts.

⚠ 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.

78
security
90
transparency
100
maintenance

Findings (2)

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec(

Pattern match low

String.fromCharCode — can build strings to evade detection

src/adapters/research_agent_adapter.js · prose · downgraded · String.fromCharCode

Why the tier is capped

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

process_exec

Is this flag fair?

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