orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a pattern where an orchestrator agent reads artifacts produced by subagents to verify their status (Rules 2 and 3). This creates a data ingestion surface.
- Ingestion points: The orchestrator reads 'artifacts' generated by subagents.
- Boundary markers: None specified in this skill.
- Capability inventory: The skill itself contains no tool definitions or scripts.
- Sanitization: Not explicitly addressed, though Rule 2 mandates checking actual artifact state rather than trusting subagent reports.
- [NO_CODE]: The skill contains no executable scripts, shell commands, or external dependencies.
Audit Metadata