Back to skill
Skillv1.0.0
ClawScan security
Agentic Marketing Auditor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 6:17 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This skill appears to be a simple documentation auditor that checks a chosen repository for README.md and llms.txt files and prints marketing-readiness recommendations.
- Guidance
- Before using it, choose the repository path intentionally. The script only checks documentation files and prints recommendations; it does not appear to modify files, contact external services, or use credentials.
Review Dimensions
- Purpose & Capability
- okThe code behavior matches the stated purpose: it checks for llms.txt, README.md, and agent-friendly README wording.
- Instruction Scope
- okThe usage is user-directed against a local repository path, and the script only reads expected documentation files at that path.
- Install Mechanism
- okNo install steps, dependencies, package installs, remote scripts, or privileged setup are requested.
- Credentials
- okThe local file access is proportionate to the auditing purpose and is limited to checking existence of llms.txt and reading README.md.
- Persistence & Privilege
- okThe artifacts show no persistence, background activity, credential use, account access, or privilege escalation.