docs-comparison-pages

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external competitor websites to extract information. This creates a surface for indirect prompt injection where malicious instructions on those websites could potentially influence the agent's behavior or output.
  • Ingestion points: External URLs of competitor websites fetched via Firecrawl or WebFetch.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore embedded instructions when the agent processes retrieved content.
  • Capability inventory: The skill reads local configuration files (e.g., pricing.ts), performs network fetches, and writes markdown documentation files.
  • Sanitization: Absent. No sanitization or validation of the fetched web content is described before its inclusion in the generated documentation.
  • [EXTERNAL_DOWNLOADS]: The skill initiates network requests to retrieve data from arbitrary competitor websites to facilitate fact-checking. This is a core part of its functional design.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 PM