trello
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the agent executing shell commands (
curlandjq) to communicate with the Trello REST API and process JSON responses. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: Untrusted data is retrieved from Trello via API responses containing board, list, and card metadata (SKILL.md).
- Boundary markers: Absent. There are no instructions to the agent to disregard instructions potentially embedded within the Trello API responses.
- Capability inventory: The agent is authorized to execute
curlandjqshell commands. - Sanitization: Absent. The skill does not include mechanisms to filter or sanitize the content returned from Trello before it is processed by the agent.
Audit Metadata