Back to skill
Skillv1.0.0
ClawScan security
ai-prompt-master · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 20, 2026, 12:36 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- Instruction-only prompt-optimization skill that contains no installs, credentials, or intrusive runtime instructions and is internally consistent with its stated purpose.
- Guidance
- This skill is instruction-only and appears safe: it helps craft prompts and does not request credentials or install code. Before using, verify the publisher if you care about provenance. Also avoid pasting sensitive secrets or private data into prompts you ask the skill to optimize, since prompt output may be sent to downstream models or logs.
Review Dimensions
- Purpose & Capability
- okThe name and description (prompt optimization for various AI tools) match the SKILL.md content. No extra capabilities, binaries, or credentials are requested that would be unrelated to prompting.
- Instruction Scope
- okSKILL.md contains only guidance for transforming user ideas into prompts (context, role, format, constraints, examples). It does not instruct the agent to read files, access environment variables, contact external endpoints, or collect unrelated system data.
- Install Mechanism
- okNo install spec and no code files are present; this is an instruction-only skill so nothing is written to disk or installed.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There are no disproportionate or unexplained secret requests.
- Persistence & Privilege
- okThe skill does not request always:true or any elevated persistence. It is user-invocable and can be invoked autonomously per platform defaults, which is expected for this kind of skill.