trello
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
cyeamcommand-line tool to perform actions such as querying boards, managing cards, and configuring webhooks.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external Trello cards that could contain adversarial instructions. - Ingestion points: Card descriptions, titles, and activity history retrieved via
cyeam trello cardsandcyeam trello card actions. - Boundary markers: The instructions lack explicit delimiters or warnings to treat data from Trello as untrusted.
- Capability inventory: The agent has the ability to upload local files to Trello (
cyeam trello card attach), modify board states, and manage webhooks. - Sanitization: No filtering or validation of the retrieved Trello content is specified before the agent processes it.
Audit Metadata