redmine-timetrack

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (HIGH): The skill exhibits a significant attack surface for Indirect Prompt Injection (Category 8).
  • Ingestion points: Untrusted data enters the agent context through the 'comments' parameter in time entry creation and update tools, as well as through data retrieved from Redmine via listing tools.
  • Boundary markers: None are present; there are no delimiters or instructions to ignore embedded commands within user-provided comments.
  • Capability inventory: The skill possesses high-privilege capabilities including the ability to create, update, and delete time entries ('redmine_create_time_entry', 'redmine_update_time_entry', 'redmine_delete_time_entry').
  • Sanitization: No evidence of sanitization, escaping, or validation of external content before it is processed or passed to tools.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 11:58 PM