gsp-repair-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external game audit findings to create roadmaps, which represents a surface for instructions embedded in data to influence agent behavior.
- Ingestion points: The skill ingests 'audit findings' and 'known issues' from external sources to generate its output.
- Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings for the input findings.
- Capability inventory: The skill is capable of writing documentation files (docs/game-studio/audit/repair-roadmap.md, docs/game-studio/audit/risk-register.md) and utilizing local markdown templates.
- Sanitization: There is no evidence of input sanitization or validation for the provided audit findings.
Audit Metadata