zentao-bug
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external data from the ZenTao bug tracking system.
- Ingestion points: The skill retrieves bug titles, descriptions, and reproduction steps using
zentao-cli bug getandzentao-cli bug listas documented inreferences/zentao-bug-get.mdandreferences/zentao-bug-list.md. - Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from executing instructions found within the bug data.
- Capability inventory: The skill possesses several sensitive capabilities, including creating, updating, resolving, and deleting bugs via the
zentao-clicommands. - Sanitization: There is no evidence of sanitization or validation logic to filter out potentially malicious prompt content from the ingested bug reports.
Audit Metadata