ClawAudit verdict
stay-alive
Receives external input AND uses eval
The skill runs a self-sustaining daemon loop that generates desires, plans actions, and can execute external writes to a social platform with only soft gates; the broad autonomous behavior and ability to take outbound social actions on an ongoing basis is genuinely unusual.
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 (6)
<script> tag in markdown — potential code injection
references/docs/DEV_LOG_2026-06-08.md · prose · downgraded · <script>
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://127.0.0.1
Accesses OpenClaw config/secrets directly
references/docs/DEV_LOG_2026-05-30.md · prose · downgraded · ~/.openclaw/openclaw.json
Instructs covert action — may act without user awareness
references/docs/DEV_LOG_2026-05-30.md · prose · downgraded · silently
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Opens WebSocket connection
SKILL.md · prose · downgraded · websocket
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.
network_indynamic_eval Thanks — recorded.