ClawAudit verdict
aig-scanner
Receives external input AND uses eval
The skill appears to be a security scanning tool that uses built-in exec and Python script to submit and query A.I.G scan tasks. It does not exhibit any malicious behavior.
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.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Findings (3)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://127.0.0.1
Python urllib.request — network access
scripts/aig_client.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/aig_client.py · prose · downgraded · os.environ.get(
Permissions & capabilities
Requires 1 system binary.
network_indynamic_eval Thanks — recorded.