ClawAudit verdict

autoresearch

karpathy-autoresearch

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Reads files AND uses eval/Function

An autonomous prompt optimization loop (mutate-evaluate-keep) that reads local skill files and runs scoring functions; dynamic_eval capability is used for its core stated purpose of running evaluation scripts, with no external exfiltration.

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.

33
security
70
transparency
70
maintenance

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.

Capability combination critical

Reads files AND uses eval/Function — may execute locally stored payloads

LLM05 · LLM06 · ASI05

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Findings (2)

Pattern match medium

subprocess execution — runs system commands from Python

scripts/loop.py · prose · downgraded · subprocess.run(

Pattern match medium

subprocess with shell=True — command injection vector

scripts/loop.py · prose · downgraded · subprocess.run( eval_cmd, shell=True

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.

dynamic_evalfile_read
Check another skill Browse the registry Auditing your own skills or configs? Use the API