skill-developer
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the provided documentation and configuration patterns confirms that the skill is focused on legitimate development workflows. No evidence of data exfiltration, hardcoded credentials, or obfuscated malicious payloads was found.
- [COMMAND_EXECUTION]: The skill documentation provides instructions on how to implement and test local automation hooks using npx tsx and Bash scripts. These scripts are intended to run within the user's project environment to provide context-aware suggestions and enforce development guardrails.
- [PROMPT_INJECTION]: The skill describes a "UserPromptSubmit" hook that injects skill suggestions directly into the model's context window. The provided templates use clear visual delimiters (e.g., ASCII borders) to help the model distinguish between injected system context and user-provided prompts, which is a recommended practice to prevent context confusion.
Audit Metadata