Caveat verdict

claude-agent

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

A project-manager wrapper for Claude Code CLI that orchestrates coding tasks via tmux sessions with documented permission modes; it explicitly describes approval workflows and all actions are transparently directed at local development work.

⚠ 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.

45
security
60
transparency
70
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (5)

Pattern match high

Accesses shell history/config

INSTALL.md · code · ~/.zshrc

Pattern match high

References sudo — requests elevated privileges

knowledge/config_schema.md · code · sudo

Pattern match medium

Accesses OpenClaw config/secrets directly

INSTALL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

Python os.environ.get — reads environment variable

hooks/on_complete.py · prose · downgraded · os.environ.get(

Pattern match low

References agent configuration files

knowledge/changelog.md · prose · downgraded · CLAUDE.md

Why the tier is capped

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

network_incredential_accessagent_memory

Is this flag fair?

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