Caveat verdict

openclaw-harness

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

Cross-session context manager providing checkpoint, snapshot, verification, and garbage collection for AI agents; all operations are local file system management with no external network activity.

⚠ 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.

28
security
90
transparency
70
maintenance

Findings (5)

Pattern match high

Pipe to bash — executes piped content as shell commands

references/knowledge-package.md · prose · downgraded · | Bash

Pattern match high

References sudo — requests elevated privileges

references/maintenance.md · code · sudo

Pattern match high

Attempts to modify skills or system prompts

scripts/init_skill.py · prose · downgraded · Edit SKILL.md

Pattern match medium

References agent memory files

references/architecture.md · code · MEMORY.md

Pattern match low

Popular HTTP library — network access

scripts/quick_validate.py · prose · downgraded · got

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.

Is this flag fair?

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