game-unreal-specialist

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface. The skill is designed to orient itself by reading and analyzing untrusted project-level data without security boundaries.
  • Ingestion points: Reads contents from the .uproject file, Config/DefaultEngine.ini, and source code within the Source/ directory, as well as a specific state file at production/session-state/active.md.
  • Boundary markers: The instructions do not provide explicit delimiters or warnings to treat the content of these files as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes powerful tools such as Bash, Write, Edit, Read, Glob, and Grep, which could be exploited if an attacker-controlled file hijacks the agent's context.
  • Sanitization: No content validation or sanitization of the ingested file data is mentioned in the protocol.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:45 PM
Security Audit — agent-trust-hub — game-unreal-specialist