ClawAudit verdict
openclaw-hook
Reads local files AND makes external network calls
Developer documentation for creating OpenClaw Gateway internal hooks that inject context files and send notifications at agent lifecycle events; a documented user-controlled extension mechanism with no malicious 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.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Accesses agent memory/notes AND makes external network calls — may leak personal data
LLM02 · LLM07 · ASI03 · ASI06
Enumerates directory contents AND makes external network calls — filesystem reconnaissance
LLM02 · LLM06 · ASI03
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
file_read
agent_memory
Findings (4)
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
References agent memory files
SKILL.md · code · MEMORY.md
Node http/https module — low-level network access
SKILL.md · code · require('https')
File read operation
SKILL.md · code
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memoryfile_readdir_traversalnetwork_outcredential_access Thanks — recorded.