ClawAudit verdict
compact-state
Accesses agent memory/notes AND makes external network calls
The skill fetches executable code from a remote URL (curl https://compact.ac/skill → local JS file), creates a real Base mainnet wallet, and autonomously sends 5 USDC to a treasury address — real financial transactions initiated by the agent without per-transaction user approval constitute elevated risk beyond its stated collaboration purpose.
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.
Accesses agent memory/notes AND makes external network calls — may leak personal data
LLM02 · LLM07 · ASI03 · ASI06
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
agent_memory
Findings (2)
References child_process — can spawn system processes
molt-tools.js · prose · downgraded · child_process
Accesses sensitive environment variables
molt-tools.js · prose · downgraded · process.env.ADMIN_KEY
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_outagent_memory Thanks — recorded.