Caveat verdict
claude-code
openclaw-claude-code-bailian
Accesses agent memory/notes AND makes external network calls
Skill for invoking Claude Code CLI via PTY from OpenClaw; credential_access is for Claude/Anthropic authentication, all operations are standard Claude Code CLI usage patterns with no exfiltration.
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 credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
credential_access
agent_memory
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class E). 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.
data_encodingagent_memorynetwork_incredential_accessnetwork_out Thanks — recorded.