Skillv1.0.0

ClawScan security

Automatic Test Generator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 30, 2026, 8:47 AM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill's stated purpose (generate unit tests) matches its instructions and requested footprint: it's an instruction-only, Node-oriented test generator that reads source code and emits test files — nothing requested is disproportionate or obviously malicious, but a few scope clarifications are missing.
Guidance: This skill appears coherent for generating unit tests, especially for JavaScript/TypeScript. Before installing or running it: 1) Review and limit the scope you give the agent (e.g., instruct it to only read src/ or specific files) so it doesn't accidentally read sensitive files like .env, credentials, or unrelated configs. 2) If you plan to generate tests for non-JS languages, remember the skill does not declare Python/Go/Java runtimes — generated tests may need language-specific tooling to run. 3) Always review generated tests before running them in CI or locally (they may include mocks, filesystem/database stubs, or expensive operations). 4) Run newly generated tests in an isolated environment if they touch external resources. If you want higher assurance, ask the publisher for clarification about multi-language support and any recommended safe defaults for repository scope.
Findings: [no-regex-findings] expected: The scanner found no regex matches because this is an instruction-only skill with no code files; that absence is expected and not evidence of safety.

Review Dimensions

Purpose & Capability: noteThe skill claims broad, multi-language test generation (Jest, Vitest, Mocha, Pytest, Go, JUnit) but the manifest only requires the node binary and the homepage is jestjs.io, which implies a JavaScript focus. Generating test code for other languages is plausible (text output) but producing 'runnable' tests for non-JS languages would normally require those language runtimes/tools; the manifest does not request them.
Instruction Scope: noteSKILL.md explicitly instructs the agent to 'analyze your code' and 'read implementation' to detect edge cases and dependencies. That is consistent with test generation, but the instructions do not limit which files to read (e.g., they don't say 'only read src/'). Because the agent will need to inspect repository files, it could read sensitive files (configuration, .env, credentials) unless the user or agent restricts scope. The instructions do not direct data to external endpoints.
Install Mechanism: okInstruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is the lowest-risk install mechanism.
Credentials: okThe skill requests no environment variables or credentials. That aligns with its stated purpose of generating test code locally; no unrelated secrets are requested.
Persistence & Privilege: okThe skill is not always-on and does not request persistent system privileges. Autonomous invocation is allowed by default but not combined with other red flags here.