skills/shotaiuchi/dotclaude/wf3-plan/Gen Agent Trust Hub

wf3-plan

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is focused on software development planning. It reads local specification files (02_SPEC.md) and configuration templates (~/.claude/templates/03_PLAN.md) to generate structured implementation plans. All operations, including file writes and git commits, are performed locally within the project context.
  • [PROMPT_INJECTION]: The skill analyzes external content from specifications and source code, creating an attack surface for indirect prompt injection.
  • Ingestion points: Reads 02_SPEC.md and various source files during the codebase investigation phase.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the input files.
  • Capability inventory: File reading and writing (03_PLAN.md, state.json) and executing git commits.
  • Sanitization: No explicit sanitization or content validation for the input files is described in the logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 07:30 AM