Caveat verdict
permission-guard
Fetches from network AND uses eval/Function
Layered permission guard system reference guide explaining Claude Code's permission model, dangerous command interception patterns, and rule priority chains; it is a security-focused educational skill.
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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Permission integrity
network_out
Findings (6)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl | bash
Pipe-to-shell pattern (wget | sh)
SKILL.md · code · wget | sh
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
References sudo — requests elevated privileges
SKILL.md · code · sudo
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/F). 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.
network_outdynamic_evalcredential_access Thanks — recorded.