zentao-story
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
zentao-clibinary to interact with the ZenTao project management system, enabling the management of stories through the command line. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated data from ZenTao, such as story titles and descriptions, which serves as a potential vector for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via the
story getandstory listcommands defined in the reference files. - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore embedded commands within the fetched data.
- Capability inventory: The skill includes commands that can modify the ZenTao database, such as
create,update, anddelete. - Sanitization: There is no evidence of sanitization or validation of the data retrieved from the ZenTao platform.
Audit Metadata