agent-team-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes prompt templates in
SKILL.mdthat interpolate external task descriptions, such as bug reports or feature requirements, into instructions for sub-agents. While this design is necessary for its orchestration purpose, the absence of explicit sanitization or strict boundary markers for placeholders like{bug_description}creates a potential surface for indirect prompt injection from untrusted input data. - [COMMAND_EXECUTION]: The orchestrator is designed to facilitate complex development tasks that involve file system modifications and terminal command execution (e.g., Git operations and bash scripts). The instructions guide the agent in using these capabilities within the established boundaries of the platform's team management features.
Audit Metadata