define-product-metrics
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify the use of data from sources such as signals, surveys, projects, account evidence, and documents, which creates an attack surface for indirect prompt injection from untrusted external content.
- Ingestion points: Identified in the 'BuildBetter Acceleration' section of SKILL.md (signals, surveys, projects, account evidence, documents, and knowledge pages).
- Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the processed data.
- Capability inventory: The skill frontmatter does not restrict tool access, meaning the agent can use any available default tools to process this data.
- Sanitization: No validation or sanitization of external content is mentioned.
Audit Metadata