update-bug
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is used for routine bug task management, including updating descriptions and status, through the One Horizon MCP. It does not perform any unauthorized actions.
- [PROMPT_INJECTION]: The skill interacts with external task data through the get-task-details tool. This pattern represents an indirect prompt injection surface as it lacks delimiters or instructions to ignore instructions that might be contained within task descriptions.
Audit Metadata