Caveat verdict
ai-security-guard
Accesses system credential store AND makes external network calls
This skill provides a documented security guard framework with pattern-based dangerous command detection, layered permission modes, and hook mechanisms for Claude Code — all implementations are transparent and the content is consistent with its security monitoring purpose.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses system credential store AND makes external network calls
LLM02 · ASI03
Permission integrity
network_out
Findings (5)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
Sets world-executable permissions
SKILL.md · code · chmod 777
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.
credential_storenetwork_out Thanks — recorded.