docs-frontmatter-description

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official Google Search documentation for SEO best practices. This is a well-known and trusted source used for instructional context.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes content from markdown files to generate metadata.
  • Ingestion points: Reads the frontmatter and the first 30 lines of body content from .md files found in the provided arguments.
  • Boundary markers: None detected. The skill does not explicitly instruct the agent to ignore or delimit instructions found within the document content.
  • Capability inventory: The skill utilizes the Edit tool to modify local documentation files based on the processed content.
  • Sanitization: No explicit sanitization or validation of the ingested document content is performed before generating the description.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 02:49 PM