Back to skill
Skillv0.2.0
ClawScan security
Skill Health Monitor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 5, 2026, 11:47 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code, documentation, and runtime instructions are coherent with its stated purpose (a local, in-memory skill-health monitor) and do not request external credentials, unusual binaries, or network endpoints.
- Guidance
- This skill appears internally consistent and lightweight: it computes health scores from metrics you pass in, keeps results in memory, and returns reports; it does not contact external services or request credentials. Before installing: (1) verify the source repository (package.json points to a GitHub URL but SKILL.md lists no homepage); (2) if you plan to enable planned features (persistence, cron, notifications) wait for or review the next release because those will require filesystem and/or network access and possibly credentials; (3) if you have sensitive data, avoid feeding metrics that reveal secrets; (4) as a best practice, review src/health-monitor.js or run the skill in a sandboxed environment first.
Review Dimensions
- Purpose & Capability
- okName/description, SKILL.md, package.json, and src/health-monitor.js all align: a lightweight health-scoring engine that accepts metric inputs, computes a 6-dimension score, applies a 3-level responsibility chain, records in-memory alerts, and returns reports. There are no unrelated requirements (no cloud creds, no external services) that contradict the stated purpose.
- Instruction Scope
- okSKILL.md instructs only on requesting health checks, batch checks, viewing alerts, and embedding the provided JS API. The runtime steps (collect → calculate → check → record → report) match the code. There are no instructions that read arbitrary system files, environment variables, or transmit data to external endpoints.
- Install Mechanism
- okThis is an instruction-only skill with a small JS implementation included; there is no install spec, no downloads, and no package dependencies. Nothing in the manifest indicates execution of third-party installers or fetching code from untrusted URLs.
- Credentials
- okThe skill declares no required environment variables, no credentials, and the code does not access process.env or external configs. The lack of secrets or unrelated env access is proportionate to its functionality.
- Persistence & Privilege
- noteThe skill stores checks and alerts in-memory (documented as a known limitation). It does not request persistent storage or system-wide configuration, and it does not modify other skills. Note: future planned features (SQLite, cron, notifications) would increase required privileges and introduce file/network operations—those should be re-reviewed if added. Autonomous invocation is enabled by default (normal for skills) but not combined here with broad privileges.