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, andlist_checklistscommands inscripts/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.pyscript. - 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