create-stories
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation (GDDs, ADRs, and Epics) and uses the extracted content to generate story files and provide context for a secondary agent task. The absence of explicit boundary markers or sanitization for this ingested content creates a potential surface for indirect prompt injection.
- Ingestion points: EPIC.md, GDD files, and ADR files loaded in Step 2.
- Boundary markers: Absent for the interpolated content.
- Capability inventory: The skill uses Task to spawn a qa-lead agent (Step 4b) and Write to create story files (Step 6).
- Sanitization: No content sanitization or filtering is performed on the ingested text.
Audit Metadata