Caveat verdict
skill-explorer
Reads files AND uses eval/Function
Provides a systematic workflow for discovering and vetting OpenClaw skills via clawhub search/inspect commands; the framework includes a safety assessment phase and all network calls are to the ClawdHub marketplace.
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.
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Both reads and writes files — verify scope is limited to intended directories
LLM06 · ASI02
Permission integrity
file_read+write
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
file_readfile_writedynamic_evaldata_encoding Thanks — recorded.