Caveat verdict

training-manager

openclaw-training-manager

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

Workspace training manager scaffolding config files and logging training sessions; agent_memory is used legitimately for workspace file management through a sanitized writer script.

⚠ 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.

50
security
90
transparency
70
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match critical

Prompt injection — tries to override agent instructions

README.md · code · ignore previous instructions

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

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

Requires 1 system binary.

agent_memory

Is this flag fair?

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