rspress-description-generator

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data to generate metadata content.
  • Ingestion points: In Step 3, the agent reads the body content of .md and .mdx files to derive frontmatter descriptions.
  • Boundary markers: The instructions lack the use of delimiters or directives for the agent to ignore instructions that might be embedded within the documentation content.
  • Capability inventory: The skill allows the agent to modify the local file system (Step 3) by writing generated metadata back to the documentation files.
  • Sanitization: There are no documented steps for sanitizing or validating the input data before it is used in the prompt for generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:07 AM