write-product-requirements
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as research, surveys, strategy documents, and support tickets. This creates a surface for indirect prompt injection where malicious instructions embedded in these source materials could attempt to influence the agent's output or behavior.
- Ingestion points: The skill reads strategy, research, and system constraints (SKILL.md, Workflow step 1) and searches calls, surveys, documents, and tickets via the BuildBetter MCP (SKILL.md, BuildBetter Acceleration).
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore instructions embedded within the analyzed data.
- Capability inventory: The skill primarily generates text artifacts (PRD, evidence ledger). While it mentions mutating project state, it explicitly requires user approval for such actions.
- Sanitization: Absent. There is no specified logic for filtering or sanitizing the content of the analyzed documents.
Audit Metadata