ue-project-context
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface.
- Ingestion points: The skill scans .uproject, Build.cs, Target.cs, and .ini files (SKILL.md).
- Boundary markers: Includes a mandatory user review and correction step before saving (SKILL.md).
- Capability inventory: The skill performs file system reads and writes to .agents/ue-project-context.md (SKILL.md).
- Sanitization: No explicit sanitization of codebase data is described.
Audit Metadata