ln-302-task-replanner
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates on project management data using authorized tools for issue tracking. No unauthorized access or data exfiltration patterns were detected.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection via external task and story data, which is mitigated by safety protocols.
- Ingestion points: Processes storyData, idealPlan, and existing task descriptions from the workspace.
- Boundary markers: No explicit data-instruction delimiters are defined for the input payloads.
- Capability inventory: Utilizes issue management tools (list_issues, update_issue, save_issue) to perform task board modifications.
- Sanitization: Employs a PreToolUse hook to validate that all created tasks contain required technical sections.
Audit Metadata