planner
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes external codebases to generate project plans. This ingestion of untrusted data creates a surface for indirect prompt injection, where malicious instructions embedded in a codebase could influence the generated task plan.
- Ingestion points: Local codebase files analyzed during research phase (SKILL.md).
- Boundary markers: None specified in the provided file.
- Capability inventory: Capability to write plan files and invoke orchestration tools like the task-orchestrator or parallel-task executor.
- Sanitization: No explicit sanitization of codebase content is described.
Audit Metadata