ue-networking-replication
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project configuration to tailor its networking advice, creating a potential vector for malicious instructions to influence the agent's output.
- Ingestion points: The Context Check section in
SKILL.mdexplicitly directs the agent to read.agents/ue-project-context.mdfor multiplayer configuration details. - Boundary markers: Absent; the instructions do not include delimiters or specific warnings to ignore embedded natural language commands within the context file.
- Capability inventory: The agent acts as an expert C++ developer with the capability to generate, modify, and advise on network-critical source code and replication logic.
- Sanitization: Absent; the skill does not provide methods for validating or filtering the contents of the context file before incorporating them into the agent's reasoning process.
Audit Metadata