Runbook Generator
Analysis
This appears to be a coherent local runbook generator that reads project configuration files and masks .env values rather than exposing secrets.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
python3 scripts/generate_runbook.py /path/to/project
The skill is operated by running a local Python script. This is expected and central to its purpose, with no evidence of hidden install-time execution or unrelated commands.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
def scan_env_file(path): ... # Mask actual values, keep examples ... info["variables"][key] = "<set in .env>"
The script reads .env-style files, which may contain credential or secret configuration, but the included code explicitly masks non-example values before including them in output.
