agency-orchestrator
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration suggests installing the "agency-orchestrator" package from npm using npx. This package is the core tool for the skill's orchestration capabilities.
- [COMMAND_EXECUTION]: The provided workflow templates instruct agents to execute common development and build commands, including "npm run build", "tsc", "eslint", and "prettier". These commands are standard for the skill's intended purpose of automating CI/CD tasks.
- [PROMPT_INJECTION]: The "parallel-research" workflow template utilizes string interpolation ("{{topic}}") to insert user-provided input into researcher agent prompts. This creates a surface for indirect prompt injection.
- Ingestion points: The "topic" variable in workflows/research.yml is populated from user input.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow prompts.
- Capability inventory: The orchestrated agents have the ability to execute shell commands (build/test) and access files as part of their defined tasks.
- Sanitization: There is no evidence of sanitization or validation of the interpolated topic string within the provided YAML templates.
Audit Metadata