vercel-agent-writing-guidelines

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches writing guidelines from Vercel Labs' official GitHub repository to define the review criteria.
  • [PROMPT_INJECTION]: The skill utilizes instructions and rules fetched from a remote Markdown file at runtime to guide the agent's analysis of documents.
  • Ingestion points: Fetches content from https://raw.githubusercontent.com/vercel-labs/writing-guidelines/main/command.md via WebFetch as specified in SKILL.md.
  • Boundary markers: The skill does not implement specific delimiters or warnings to isolate the fetched instructions from the primary prompt context.
  • Capability inventory: The skill possesses network access via WebFetch and read access to the local filesystem for the files being reviewed.
  • Sanitization: There is no explicit sanitization of the remote content before it is processed as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:46 PM
Security Audit — agent-trust-hub — vercel-agent-writing-guidelines