prompt-authoring
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill is composed of instructional markdown and does not perform network operations or execute code at runtime. It actively promotes secure design by advising against reliance on inaccessible context and emphasizing output validation.
- [EXTERNAL_DOWNLOADS]: The skill includes an installation command that references a GitHub repository owned by the author (aelaguiz/authoring-skills.git).
- [COMMAND_EXECUTION]: An npx command is provided for the installation of the skill.
- [PROMPT_INJECTION]: The skill processes external text, creating an indirect prompt injection surface. 1. Ingestion: Inputs include user-provided prompts (workflow-and-modes.md). 2. Boundary markers: Guidelines require sticking strictly to the prompt context (SKILL.md). 3. Capability inventory: The skill is restricted to text analysis and refactoring. 4. Sanitization: Uses structured output contracts to validate results.
Audit Metadata