discover-opportunities
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer feedback data, which introduces a potential surface for indirect prompt injection.
- Ingestion points: Feedback is retrieved via get_feedback_insights, get_feedback_mentions, and get_feedback_comments in Phase 2d of SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for these ingestion points.
- Capability inventory: The skill lacks capabilities for shell execution, file writing, or non-whitelisted network communication, limiting the potential impact of an injection.
- Sanitization: No sanitization or validation of the external feedback content is described.
Audit Metadata