agent-agent-organizer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The metadata.json file provides an installation command that fetches the SKILL.md file from a third-party GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a role for task orchestration and multi-agent coordination, which involves processing external data that could contain embedded instructions.
- Ingestion points: The agent uses tools like task-queue and interacts with other agents to perform orchestration (SKILL.md).
- Boundary markers: None provided; the instructions do not include delimiters or specific commands to ignore instructions within ingested task data.
- Capability inventory: The skill utilizes tools for Read, Write, agent-registry, task-queue, and monitoring.
- Sanitization: No validation or sanitization requirements for external task content are described.
Audit Metadata