titans
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill analyzes untrusted code provided by users, creating a surface for indirect prompt injection attacks.
- Ingestion points: Code files are scoped via the /titans command and passed to sub-agents as described in SKILL.md.
- Boundary markers: Absent; the orchestration logic does not specify delimiters to separate reviewer instructions from analyzed code.
- Capability inventory: Uses Explore sub-agents with Opus-level reasoning and broad context access.
- Sanitization: No sanitization or filtering of input code is performed.
Audit Metadata