zentao-project

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the management of ZenTao projects by executing the zentao-cli binary. It supports listing, retrieving, creating, updating, and deleting project entities through subcommands.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied data which is then used as arguments for command-line operations, creating a potential vector for command injection or prompt manipulation.
  • Ingestion points: The skill accepts user-provided text for project names, codes, and descriptions, notably in references/zentao-project-create.md and references/zentao-project-update.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within user input are present in the skill files.
  • Capability inventory: The skill utilizes zentao-cli for state-changing operations including create, update, and delete within the ZenTao environment.
  • Sanitization: There are no explicit instructions or regex patterns provided to sanitize or escape user-supplied strings before they are passed to the shell-executed binary.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:26 AM
Security Audit — agent-trust-hub — zentao-project