using-trello-cli

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill operates by executing trello CLI commands to perform actions on Trello boards, lists, and cards.
  • [DYNAMIC_EXECUTION]: The skill instructs the agent to compile the trello binary from local source code using go build if the executable is not already present on the system.
  • [DATA_EXFILTRATION]: The command attachments add-file enables the agent to read local files and upload them to Trello. This capability could be used to exfiltrate sensitive local files if an attacker successfully tricks the agent into targeting sensitive file paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from Trello resources, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted content is retrieved using trello cards get, trello comments list, and trello search (found in SKILL.md and references/command-digest.md).
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to disregard instructions found in the retrieved data.
  • Capability inventory: The skill possesses command execution, local file read access, and the ability to perform network write operations via the Trello API.
  • Sanitization: No sanitization or filtering is applied to the data retrieved from Trello before it is used by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 12:04 PM