opportunity-solution-tree
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process customer research data, including interviews, surveys, and feedback, which are untrusted external sources.
- Ingestion points: Processes research data, interview transcripts, and customer feedback provided in the prompt context or via files (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters or specific 'ignore instructions' warnings for the research data being processed.
- Capability inventory: The skill can generate text analysis and save output as markdown files.
- Sanitization: Absent. There is no explicit logic to filter or sanitize potential prompt injection attacks embedded within the provided research artifacts.
Audit Metadata