ClawAudit verdict
auto-optimizer
Fetches from network AND uses eval/Function
An iterative optimization engine that uses git revert for bad changes and local eval scripts; the dynamic_eval capability is clearly used for running user-supplied metric scripts locally as part of the optimization loop.
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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read
Findings (3)
Uses eval() — can execute arbitrary code
SKILL.md · frontmatter · eval (
apt-get install — installs system packages
SETUP.md · code · apt-get install
Python urllib.request — network access
SKILL.md · code · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C/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.
dynamic_evalnetwork_outfile_read Thanks — recorded.