ClawAudit verdict
skill-creator
skill-creator-opencode
Encodes data AND uses eval
Automates skill creation and iteration using the Opencode CLI to run prompts and evals; all operations are local tool invocations and the auto-detection of opencode binary path is a benign configuration step.
Automated static analysis — not a human review. ClawAudit 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 ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Findings (3)
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · without telling
subprocess execution — runs system commands from Python
eval-viewer/generate_review.py · prose · downgraded · subprocess.run(
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
data_encodingdynamic_eval Thanks — recorded.