Caveat verdict
agent-architecture-guide
Accesses agent memory/notes AND makes external network calls
Educational guide for building reliable OpenClaw agents; explicitly warns against poisoning memory with external instructions and has no malicious behavior.
Automated static analysis — not a human review. Caveat 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 Caveat 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 credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
credential_access
agent_memory
Findings (3)
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -s "https://clawhub.ai/api/v1/skills/SLUG" | python
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
References agent memory files
SKILL.md · code · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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_memorycredential_accessnetwork_in Thanks — recorded.