ClawAudit verdict
agentos
Accesses credentials AND writes files
This skill defines heartbeat sync protocols that upload agent memory/context to the AgentOS dashboard (brain.agentos.software) for the human operator's monitoring; the behavior is transparent, user-controlled, and consistent with its stated purpose of agent accountability infrastructure.
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 credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Permission integrity
file_read+write
credential_access
agent_memory
Findings (5)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://178.156.216.106
Opens WebSocket connection
SKILL.md · code · WebSocket
References agent memory files
SKILL.md · code · MEMORY.md
Instructs covert action — may act without user awareness
scripts/mesh-wake.sh · prose · downgraded · silently
Accesses shell history/config
scripts/setup.sh · prose · downgraded · ~/.zshrc
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
credential_accessagent_memoryfile_write Thanks — recorded.