speckit-analyze

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script at .specify/scripts/bash/check-prerequisites.sh during initialization. This script is used to verify the project environment and locate necessary files before analysis begins.
  • [PROMPT_INJECTION]: The skill processes content from untrusted local markdown files (spec.md, plan.md, tasks.md), which represents an indirect prompt injection surface.
  • Ingestion points: Reads spec.md, plan.md, and tasks.md from the project's feature directory.
  • Boundary markers: The skill does not implement explicit boundary markers or instructions to ignore embedded agent directives within the analyzed files.
  • Capability inventory: The skill executes a local bash script at startup but is otherwise constrained to read-only operations.
  • Sanitization: Content is parsed into semantic models for the purpose of generating a consistency report rather than being used to construct executable commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:47 PM