Back to skill
Skillv1.0.0
ClawScan security
Prompt Engineering Expert · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 4:51 AM
- Verdict
- Benign
- Confidence
- medium
- Model
- gpt-5.5
- Summary
- This is a coherent instruction-only prompt engineering skill with no declared code, install steps, credentials, persistence, or sensitive system access.
- Guidance
- This skill appears safe to install as a documentation-based prompt engineering helper. As with any prompt-design tool, review generated prompts before using them in important workflows, especially if they will control agents with tools or account access.
Review Dimensions
- Purpose & Capability
- okThe stated purpose—prompt engineering guidance, prompt refinement, custom instruction design, and testing advice—matches the provided instructions and documentation excerpts.
- Instruction Scope
- okThe skill frames itself as analysis and guidance only, with documented limitations stating it does not execute code, run prompts, access real-time data, or call external APIs.
- Install Mechanism
- okNo install spec, required binaries, environment variables, credentials, or code files are declared; the skill is presented as instruction-only documentation.
- Credentials
- okThe artifacts do not request local filesystem, network, API, credential, or OS-level authority beyond user-supplied prompt content.
- Persistence & Privilege
- okNo persistence mechanism, background process, privilege escalation, credential use, or autonomous mutation authority is shown in the provided artifacts.