nitro-task-planner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted external data such as user feedback, parity goals, and feature briefs to generate tasks and updates.
- Ingestion points: Untrusted user input is processed during planning sessions as described in the 'The role' and 'Before writing tasks' sections.
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The agent uses tools including
nitro agent tasks create,nitro agent memory save, andnitro agent mail sendto store and transmit data. - Sanitization: The 'Task quality bar' enforces a strict format (Problem, File scope, Fix direction, Verification, Non-goals), which serves as a validation mechanism for the output content.
Audit Metadata