writing-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches writing rules and instructions from the Vercel Labs repository on GitHub to guide the review process.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from both a remote URL and user-provided local files, which presents a surface for potential instruction injection.
- Ingestion points: Remote content fetched via WebFetch and local files read for auditing (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the audited documents.
- Capability inventory: File system read access and network fetching capabilities (SKILL.md).
- Sanitization: No specific filtering or escaping is applied to the data retrieved from external sources before processing.
Audit Metadata