trello

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and processes data from an external, potentially untrusted source.
  • Ingestion points: The skill fetches board names, list names, card names, and descriptions from the Trello API via curl commands in SKILL.md.
  • Boundary markers: The instructions do not define clear boundaries or provide guidance to the agent to disregard instructions that might be embedded within the Trello card content.
  • Capability inventory: The skill uses curl for API interactions and jq for parsing JSON responses.
  • Sanitization: There is no evidence of content sanitization or validation to prevent the agent from obeying instructions hidden in Trello card metadata or descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 05:04 AM