trello-use
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents how to ingest data from Trello cards, lists, and comments, which constitutes a potential attack surface if the retrieved content contains malicious instructions intended for the agent.
- Ingestion points: Data retrieved from Trello via
trelloReadCard(including comments, labels, and descriptions) andtrelloReadListtools as described in the documentation. - Boundary markers: The skill does not instruct the agent to use specific delimiters or 'ignore instructions' markers when processing content retrieved from the Trello API.
- Capability inventory: The skill enables the agent to perform write operations across the Trello environment using
trelloWriteCard,trelloWriteList, andtrelloWritePlanner. - Sanitization: The instructions do not define or recommend sanitization or validation of the text content fetched from external Trello sources before the agent processes it.
Audit Metadata