trello-use

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of non-executable technical instructions designed to guide an agent in using Trello-specific tools. It promotes best practices like structural validation via ARIs and standardized timezone handling.
  • [PROMPT_INJECTION]: The skill facilitates the processing of untrusted data from an external source (Trello), which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is pulled from Trello via trelloReadMember, trelloReadBoard, trelloReadCard, trelloReadInbox, trelloReadPlanner, and trelloSearch in SKILL.md.
  • Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the retrieved Trello content are defined in this skill.
  • Capability inventory: The skill allows writing data back to the platform via trelloWriteCard, trelloWriteChecklist, trelloWriteInbox, trelloWritePlanner, and trelloWriteList in SKILL.md.
  • Sanitization: The skill relies on the underlying MCP tools for input validation rather than performing explicit content sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 11:43 PM
Security Audit — agent-trust-hub — trello-use