ClawAudit verdict
agent-network
Receives external input AND executes processes
Multi-agent group chat collaboration system implemented as a local Python library; no external data transmission or deceptive 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 executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Findings (3)
References webhook/callback URL
references/ADVANCED.md · code · webhook_url
os.system/popen — direct OS command execution
scripts/cli.py · prose · downgraded · os.system(
Python directory traversal
references/ADVANCED.md · code · os.listdir(
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.
network_inprocess_exec Thanks — recorded.