ue-gameplay-cameras
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read local project context from '.agents/ue-project-context.md'. This ingestion point creates an indirect prompt injection surface if the context file contains malicious instructions intended to manipulate the agent's behavior during code generation or project configuration tasks.
- Ingestion points: '.agents/ue-project-context.md' (referenced in SKILL.md).
- Boundary markers: Absent. No explicit delimiters or instructions are provided to the agent to treat external context data as untrusted or to disregard instructions within the file.
- Capability inventory: The skill facilitates the creation and modification of C++ classes, build configurations, and plugin management within an Unreal Engine project.
- Sanitization: Absent. The skill does not provide mechanisms for validating or sanitizing the content of the project context file.
Audit Metadata