pick-next-prompt

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill manages a structured implementation plan stored in local files (.turbo/prompts.md and .turbo/spec.md). It does not contain any malicious code or instructions.
  • [DATA_EXFILTRATION]: The skill reads project-specific configuration and documentation files. This access is restricted to the local environment and is necessary for the skill's primary function of providing context-aware implementation planning.
  • [PROMPT_INJECTION]: The skill processes natural language prompts from .turbo/prompts.md to guide its next actions. Ingestion points: The skill reads task descriptions and requirements from .turbo/prompts.md and .turbo/spec.md. Boundary markers: No explicit delimiters or safety instructions are used when interpolating these prompts. Capability inventory: The skill can read/write local project files and invoke other installed skills like /enhance-plan. Sanitization: No sanitization of the input prompt text is performed before it is used to design the implementation plan. This is the primary intended behavior of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 08:45 PM