zentao-product

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks where malicious instructions are embedded in product data.\n
  • Ingestion points: Untrusted data enters the agent context via product names, codes, and descriptions retrieved from zentao-cli product list and zentao-cli product get (referenced in SKILL.md).\n
  • Boundary markers: The instructions do not define any delimiters or provide warnings to the agent to ignore instructions embedded within the product data.\n
  • Capability inventory: The skill provides full lifecycle management capabilities, including the ability to create, update, and delete products via zentao-cli (as seen in references/zentao-product-create.md and references/zentao-product-delete.md).\n
  • Sanitization: There are no documented procedures for sanitizing or validating external product content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill relies on the execution of the zentao-cli binary to perform its operations. While this is the intended functionality, it provides a vector for the agent to modify the remote ZenTao environment based on potentially malicious inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:26 AM
Security Audit — agent-trust-hub — zentao-product