Back to skill
Skillv1.0.0
ClawScan security
Ai Prompt Templates · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:36 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is a coherent instruction-only collection of AI prompt templates with no code, credentials, install scripts, hidden automation, or account access.
- Guidance
- This appears safe to install as a prompt-template pack. As with any prompt collection, avoid pasting secrets, private customer data, or proprietary code into an external LLM unless you intend to share that information with that model provider.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a prompt-template collection for code review, content creation, analysis, education, and problem solving.
- Instruction Scope
- okThe templates are user-facing prompt text with placeholders; they do not instruct the agent to override user intent, force tool use, or perform autonomous actions.
- Install Mechanism
- okThere is no install spec, no required binaries, and no code. The README only shows user-directed install/copy examples for template files.
- Credentials
- okThe skill does not request environment variables, credentials, network access, broad local file access, or external service permissions.
- Persistence & Privilege
- okNo persistence, background workers, privilege escalation, account access, or long-running behavior is evidenced in the artifacts.