writing-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill optionally fetches configuration and updated guidelines from Vercel Labs' official GitHub repository (
raw.githubusercontent.com/vercel-labs/writing-guidelines). This is a reference to a trusted organization for maintaining current linting rules. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided files, which creates an attack surface where instructions embedded within a document could attempt to influence the agent's behavior during the review process.
- Ingestion points: User-specified files or patterns provided as arguments to the review command.
- Boundary markers: The instructions in
references/guidelines.mddo not explicitly include delimiters or "ignore embedded instructions" warnings for the content being reviewed. - Capability inventory: The skill possesses file reading and text output capabilities.
- Sanitization: No explicit sanitization or filtering of the input file content is defined.
Audit Metadata