trello
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Trello API andjqfor parsing JSON responses. These are standard command-line tools used for their intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Trello), which could contain malicious instructions designed to influence the agent.
- Ingestion points: Trello board names, list names, card names, descriptions, and comments fetched via
curlcommands inSKILL.md. - Boundary markers: None identified. There are no delimiters or instructions to treat the retrieved content as data rather than instructions.
- Capability inventory: The skill has the ability to execute network requests via
curl(GET, POST, PUT) and manipulate JSON viajq. - Sanitization: None identified. Content retrieved from Trello is passed directly to the agent's context without filtering or escaping.
Audit Metadata