trello-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from Trello card descriptions, board names, and checklist items.
  • Ingestion points: Data enters the agent context through list_boards, list_cards, and list_checklists commands in scripts/trello_api.py.
  • Boundary markers: No explicit delimiters or instructions are used to separate Trello data from the agent's system instructions.
  • Capability inventory: The skill allows full CRUD operations (Create, Read, Update, Delete) on Trello boards and cards via the scripts/trello_api.py script.
  • Sanitization: The script performs no sanitization or filtering of the text content retrieved from the Trello API before outputting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM