define-product-vision

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ground its analysis in external data sources including customer evidence, knowledge pages, documents, and survey responses.
  • Ingestion points: The 'BuildBetter Acceleration' section in SKILL.md specifies searching organization skills, documents, and survey responses.
  • Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or sanitizes instructions that might be embedded within these external documents.
  • Capability inventory: The skill is primarily designed for generating text-based artifacts (vision narratives, principles). It does not appear to have capabilities for file modification or outbound network communication.
  • Sanitization: No sanitization steps are defined for the data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 03:14 AM