write-product-decision

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 ingest and synthesize information from various external and potentially untrusted sources to create decision records.
  • Ingestion points: The 'BuildBetter Acceleration' section in SKILL.md specifies that the agent should use project details, documents, knowledge pages, customer evidence, surveys, and calls.
  • Boundary markers: None present. The instructions do not include delimiters or specific guidance for the agent to ignore instructions embedded within the ingested data.
  • Capability inventory: Low. The skill is focused on generating documentation. While it mentions the 'BuildBetter MCP' for searching and referencing IDs, it explicitly states that creating or changing records in external systems requires approval.
  • Sanitization: No sanitization, validation, or escaping of the external content is prescribed in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 03:14 AM