task-planning

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a legitimate and controlled workflow for task management within a software development environment. It uses abstract tools like updateTask to handle task lifecycle management based on specific design inputs.
  • [PROMPT_INJECTION]: The skill is designed to process data from project files such as design.json, openapi.yaml, and wireframes.dsl (Category 8: Indirect Prompt Injection surface).
  • Ingestion points: design.json, openapi.yaml, and wireframes.dsl in SKILL.md.
  • Boundary markers: None explicitly defined; however, the agent is instructed to extract specific fields (like stories) rather than execute general content.
  • Capability inventory: The skill utilizes the updateTask tool to write and update implementation plans.
  • Sanitization: No specific sanitization logic is described, but the instructions focus on structured data mapping which limits the impact of potential injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 03:14 PM
Security Audit — agent-trust-hub — task-planning