orchestration
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project content and investigation results that could contain malicious instructions designed to influence the agent. Ingestion points: Project files and facts identified during investigations (SKILL.md). Boundary markers: Present. The skill uses a WORKER AGENT preamble and structured fields to delimit worker instructions. Capability inventory: The orchestrator can spawn sub-agents and execute project-wide commands (SKILL.md). Sanitization: Absent. There is no instruction to sanitize data extracted from files before it is included in prompts.
- [COMMAND_EXECUTION]: The skill authorizes the agent to execute build, lint, and test suites, which triggers the execution of scripts defined in the project environment.
Audit Metadata