Trello Automation

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines automation workflows that ingest untrusted data from Trello cards, which represents an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context via card metadata and body fields such as {{detailed_description}}, {{content_title}}, and {{task_name}} in SKILL.md.
  • Boundary markers: Absent. The skill uses template placeholders for data interpolation but does not specify delimiters or instructions for the agent to ignore potentially malicious directives embedded within that data.
  • Capability inventory: The skill employs tools for card management and board automation (trello_card, trello_automation) and features a Slack integration for automated notifications.
  • Sanitization: Absent. There are no instructions for validating, filtering, or escaping the content retrieved from external cards before it is processed or output to other channels.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 02:52 PM
Security Audit — agent-trust-hub — Trello Automation