docs-frontmatter-description
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official SEO guidelines from a Google developers URL. This is a trusted external source used for context.
- [INDIRECT_PROMPT_INJECTION]: The skill reads existing documentation content to generate meta descriptions, which constitutes a potential ingestion surface for untrusted data. However, the risk is minimal due to strict output constraints. 1. Ingestion points: Markdown files (.md) are read from the directory path provided in $ARGUMENTS or discovered via the Glob tool. 2. Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the processing logic. 3. Capability inventory: The skill utilizes Read, Grep, Glob, and Edit tools to modify files in the repository. 4. Sanitization: Input content is not sanitized, but the output is restricted to plain text under 200 characters and follows rigid structural patterns.
Audit Metadata