zentao-project

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the zentao-cli binary to perform project management tasks, including listing, creating, and deleting projects. These operations are executed as shell commands.\n- [PROMPT_INJECTION]: A vulnerability surface for indirect prompt injection is present because the skill retrieves and displays project information (names, descriptions) which could contain untrusted instructions from the ZenTao database.\n
  • Ingestion points: Untrusted data enters the agent context via zentao-cli project list and zentao-cli project get (referenced in zentao-project-list.md and zentao-project-get.md).\n
  • Boundary markers: Absent. There are no instructions to the agent to treat project-sourced data as non-executable text or to ignore embedded instructions.\n
  • Capability inventory: The skill has the capability to execute shell commands and modify project data via the zentao-cli tool.\n
  • Sanitization: Absent. The skill does not perform content validation or escaping on the data returned from the ZenTao API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 06:11 AM
Security Audit — agent-trust-hub — zentao-project