Caveat verdict

agent-context-system

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

A local-only markdown-based memory system for AI agents that reads and writes two local files (AGENTS.md and .agents.local.md); all operations are transparent, user-approved, and no data leaves the machine.

⚠ 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
100
transparency
80
maintenance

Findings (3)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf /

Pattern match medium

References agent configuration files

SKILL.md · code · CLAUDE.md

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · quietly

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