coordinator

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONPERSISTENCE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The coordinator is designed to read and process standing-rules.md and reports generated by 'worker' agents, which could contain instructions to influence the coordinator's behavior.
  • Ingestion points: Reads project.md, standing-rules.md, and markdown reports from the reports/ directory.
  • Boundary markers: No specific escaping or boundary markers are used when interpolating report content into the coordinator's context.
  • Capability inventory: The coordinator can execute shell commands (t3, gh, git), delegate new tasks, and schedule timers.
  • Sanitization: While the project.py script escapes markdown pipes for table formatting, it does not sanitize natural language instructions, potentially allowing a malicious worker to influence the coordinator's behavior through its report content.
  • [COMMAND_EXECUTION]: The skill uses a Python script (scripts/project.py) to execute shell commands via subprocess.run. These commands interact with git, gh (GitHub CLI), and t3 (a thread management tool).
  • Evidence: The script extracts thread links and PR references using regular expressions (LINK and PR_REF in project.py) to validate parameters before passing them to CLI tools.
  • [PERSISTENCE]: The skill includes a background 'tick' mechanism for project monitoring that persists across sessions.
  • Evidence: references/tick.md and scripts/tick.sh provide instructions for installing OS-level services (macOS LaunchAgents or Linux systemd timers). This behavior is documented and requires manual user intervention to set up.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 08:30 AM