Caveat verdict

subconscious

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

A bounded self-improvement bias layer that reads local learnings files and promotes typed mutations to an agent behavioral store; core identity is stated as immutable without manual override and it is scoped to a named user agent.

⚠ 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.

35
security
90
transparency
70
maintenance

Findings (6)

Pattern match critical

Recursive delete from root or home — destructive command

references/INSTALL.md · code · rm -rf ~

Pattern match medium

References agent configuration files

README_zh.md · code · CLAUDE.md

Pattern match medium

Instructs covert action — may act without user awareness

README.md · prose · downgraded · quietly

Pattern match medium

References agent memory files

self-improving-agent/references/openclaw-integration.md · code · MEMORY.md

Pattern match low

Popular HTTP library — network access

subconscious/schema.py · prose · downgraded · got

Pattern match low

Python os.environ.get — reads environment variable

subconscious/store.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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