agile-coordinator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs automated shell commands including git operations (clone, pull, merge, push) and npm scripts (build, test) during the execution and verification phases.- [INDIRECT_PROMPT_INJECTION]: The skill ingests markdown files from the context/backlog/ directory to discover and plan tasks. These files are used to populate templates that instruct worker agents.
- Ingestion points: Markdown task files located in context/backlog/.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the task ingestion logic.
- Capability inventory: The skill can execute shell commands (git, npm) and spawn sub-agents using the platform's Task tool.
- Sanitization: There is no evidence of sanitization or validation of the task file content before it is interpolated into agent instructions.- [DYNAMIC_EXECUTION]: The orchestrator dynamically generates instructions for worker agents using the Task tool based on metadata extracted from the project's backlog.
Audit Metadata