Back to skill
Skillv3.0.2
ClawScan security
Container Runner · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 24, 2026, 1:13 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent with its documentation: it is an instruction-only reference tool that prints local help text and does not request credentials, install software, or make network calls.
- Guidance
- This skill appears to be a benign, local reference tool that prints static documentation. If you plan to let the agent invoke it autonomously, note the agent will execute the included script locally when called (it only prints text). You may want to: 1) verify the small script is acceptable to run in your environment (it doesn't access network or secrets); 2) ignore the minor version/metadata inconsistencies (harmless documentation drift); and 3) if you prefer to avoid any autonomous execution at all, disable model invocation for the skill in your agent settings.
Review Dimensions
- Purpose & Capability
- noteName/description match the included files: SKILL.md and scripts/script.sh provide reference documentation and command output. Minor inconsistencies: registry/version metadata (3.0.2), SKILL.md header (3.0.1) and script VERSION (3.0.0) differ, and the quickstart text generically mentions "Required tools and access credentials" even though the skill itself does not require or request any credentials — these are documentation artifacts rather than functional mismatches.
- Instruction Scope
- okSKILL.md states the skill outputs plain-text heredocs and requires no network or credentials. The included script simply prints static documentation for commands and does not read unspecified files, environment variables, or invoke network endpoints.
- Install Mechanism
- okNo install specification is provided and the skill is effectively instruction-only with a small helper script. Nothing is downloaded or written to disk by an installer; risk from installation is minimal.
- Credentials
- okThe skill declares no required environment variables, no credentials, and the script does not read or use env vars or secret-like paths. Requested privileges are proportional (none).
- Persistence & Privilege
- okalways is false, the skill does not request persistent presence or modify other skill/system configs. Autonomous invocation is permitted by default (platform normal) but the skill's actions are limited and local.