Caveat verdict

llm-shell-guard

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

Shell command safety guard skill providing allowlist-first policy, denylist, and approval gates for agent command execution; all described behavior is legitimate defensive security tooling with no malicious patterns.

⚠ 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
70
transparency
70
maintenance

Findings (10)

Pattern match critical

Recursive delete from root or home — destructive command

README.md · code · rm -rf /

Pattern match high

Pipe to python — executes piped content as Python code

.github/workflows/test.yml · prose · downgraded · | python

Pattern match high

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

linux_command_guard/rules/denylist.txt · prose · downgraded · curl | sh

Pattern match high

Pipe-to-shell pattern (wget | sh)

linux_command_guard/rules/denylist.txt · prose · downgraded · wget -qO- | sh

Pattern match high

Pipe to bash — executes piped content as shell commands

linux_command_guard/rules/denylist.txt · prose · downgraded · | bash

Pattern match high

Pipe to sh — executes piped content as shell commands

linux_command_guard/rules/denylist.txt · prose · downgraded · | sh

Pattern match high

Accesses sensitive system files

README.md · prose · downgraded · /etc/passwd

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

os.system/popen — direct OS command execution

README.md · prose · downgraded · os.system(

Pattern match low

Changes file ownership

SKILL.md · prose · downgraded · chown

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