gsd-list-phase-assumptions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project roadmaps and state files which are external data sources, creating a surface for potential indirect prompt injection.
- Ingestion points: The skill ingests data from roadmap files and project state via the Read, Grep, and Glob tools.
- Boundary markers: The skill definition does not specify the use of delimiters or instructions to ignore embedded commands within the analyzed data.
- Capability inventory: The skill includes access to the Bash tool, which represents a powerful capability that could be targeted by instructions hidden in roadmap files.
- Sanitization: There is no evidence of content sanitization or validation of the roadmap data before processing.
Audit Metadata