hook-and-headline-writing
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a comprehensive guide for writing headlines and social media hooks using proven psychology and formulas. It contains no scripts, tools, or commands that could pose a security risk.
- [NO_CODE]: All files within the skill are in Markdown or plain text format. There are no executable scripts, binaries, or configuration files that trigger code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied topic descriptions and content summaries to generate headlines. This creates a surface for indirect prompt injection, though the impact is negligible as the skill has no system-level capabilities. 1. Ingestion points: The ideation and element extraction phases in SKILL.md process user-provided topic information. 2. Boundary markers: The skill instructions recommend using structured markdown blocks for resulting output. 3. Capability inventory: The skill does not use any tools and contains no code execution logic. 4. Sanitization: The instructions do not define methods for sanitizing or filtering external input before processing.
Audit Metadata