review-business
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from '.business/context.md', metric files, and backlogs which are ingestion points for external data. This creates a surface for indirect prompt injection.
- Ingestion points: Reads '.business/context.md', metrics, prior reviews, and backlog.
- Boundary markers: Absent; there are no specific instructions to ignore embedded commands within these data files.
- Capability inventory: Can append to local files in '.business/reviews/' and update the backlog or context.
- Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.
Audit Metadata