game-build-log-triage
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of processing untrusted external data (game engine logs).
- Ingestion points: The agent ingests raw text from Unity and Unreal Engine logs, CI transcripts, and console excerpts using the
ReadandGreptools. - Boundary markers: Absent. The skill instructions do not require the use of delimiters or specify that the agent should ignore instructions embedded within the logs it analyzes.
- Capability inventory: The skill is configured with
Bash,Read,Write,Edit,Glob, andGrepcapabilities, allowing it to interact extensively with the local filesystem. - Sanitization: Absent. There are no verification or sanitization steps mentioned to filter malicious payloads that might be hidden in processed log files.
Audit Metadata