Trello Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content such as card descriptions, board configurations, and automation rules, which represents a potential surface for indirect prompt injection if the source data is controlled by an adversary.
- Ingestion points: Card descriptions, board names, and template variables (
{{detailed_description}},{{topic}},{{audience}}) in SKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted data from instructions.
- Capability inventory: Tools for board, list, and card manipulation via the
project-mcpserver. - Sanitization: The provided templates do not include explicit sanitization or validation steps for input data.
Audit Metadata