map-product-opportunities
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 external data sources including survey responses, customer call transcripts, and project documents. This creates a surface for indirect prompt injection where instructions hidden within these source materials could attempt to manipulate the agent's logic or output.
- Ingestion points: The 'BuildBetter Acceleration' section in SKILL.md identifies signals, survey responses, calls, and documents as primary input sources for the opportunity mapping process.
- Boundary markers: The skill instructions do not define specific delimiters or provide guidance to the agent to ignore embedded instructions within the source evidence.
- Capability inventory: The skill primarily generates analytical text artifacts and does not exhibit high-risk capabilities such as arbitrary command execution, network exfiltration, or filesystem modification.
- Sanitization: There are no requirements or instructions provided for the sanitization, escaping, or validation of the external content before it is incorporated into the agent's reasoning context.
Audit Metadata