arena
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and evaluate candidate outputs produced by multiple subagents, which represents a surface for indirect instructions to influence the agent's judging and synthesis logic.
- Ingestion points: Phase D requires the agent to "Read every candidate end to end before picking."
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the candidate outputs.
- Capability inventory: The skill utilizes subagent spawning (via
run_in_background: true) and file system access for managing candidate output paths. - Sanitization: No explicit sanitization or validation of the subagents' content is performed before it is processed by the parent agent.
Audit Metadata