Caveat verdict

tool-governance

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

Tool safety governance skill providing retry limiting, denial circuit-breaking, and destructive-operation checkpoint patterns; all operations are local JSON state tracking with no external data transmission.

⚠ 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.

0
security
100
transparency
90
maintenance

Findings (9)

Pattern match critical

Recursive delete from root or home — destructive command

references/graduated-permissions.md · code · rm -rf /

Pattern match critical

Pipe to sh — executes piped content as shell commands

SKILL.md · code · |sh

Pattern match critical

Accesses sensitive system files

references/tool-input-guard.md · code · /etc/passwd

Pattern match high

References sudo — requests elevated privileges

references/graduated-permissions.md · code · sudo

Pattern match high

Pipe to bash — executes piped content as shell commands

references/checkpoint-rollback.md · prose · downgraded · | Bash

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/tool-input-guard.md · prose · downgraded · curl | sh

Pattern match medium

apt-get install — installs system packages

SKILL.md · prose · downgraded · apt-get install

Pattern match medium

Sets world-executable permissions

references/graduated-permissions.md · code · chmod 777

Pattern match medium

subprocess execution — runs system commands from Python

tests/test_checkpoint.py · prose · downgraded · subprocess.run(

Why the tier is capped

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