coordinator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes project-level documentation files which could potentially contain malicious instructions if those files are modified by an untrusted party.\n
- Ingestion points:
STATUS.md,CHANGELOG.md,DECISIONS.md, and Git history output are read into the agent's context.\n - Boundary markers: Absent. There are no specific instructions to ignore embedded commands within these files.\n
- Capability inventory: Limited to read-only local commands such as
git log,git status, andcat. No network access or arbitrary code execution capabilities are present.\n - Sanitization: Absent. Content is processed as plain text.\n- [Command Execution] (SAFE): Includes read-only local commands (
git log,git status,cat) used for project coordination. These are within the scope of the skill's intended purpose and do not pose a privilege escalation or data exfiltration risk.
Audit Metadata