writing-style-guide
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-provided text, creating a surface for potential instructions embedded in that data. 1. Ingestion points: The skill instructions in SKILL.md and its description specify that the agent is to 'Write or review human-facing text'. 2. Boundary markers: No explicit instructions (such as delimiters or 'ignore instructions' warnings) are provided to the agent to distinguish style guide instructions from user input. 3. Capability inventory: Static analysis of all provided documentation confirms no use of shell tools, network operations, or file system write capabilities. 4. Sanitization: No input validation or sanitization logic is present in the markdown-based documentation.
- [NO_CODE]: The skill consists entirely of markdown reference files and YAML configuration. No executable scripts (Python, JavaScript, or shell) are included in the package.
Audit Metadata