Caveat verdict
claw-doctor
Reads local files AND makes external network calls
This skill diagnoses and repairs OpenClaw skill configuration issues by reading local skill files and running diagnostic shell commands; file_read and credential_access are used only to inspect the local OpenClaw config, not to exfiltrate data.
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.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
file_read
credential_access
package_install
Findings (5)
Possible hardcoded credential
SKILL.md · code · API_KEY="their-key-here
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
pip3 install — installs Python packages at runtime
SKILL.md · code · pip3 install
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). 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_outpackage_installfile_readcredential_access Thanks — recorded.