speckit-analyze

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script .specify/scripts/bash/check-prerequisites.sh using the repository root as the context. This is a standard prerequisite check for the toolset and uses escaped arguments for safety.
  • [DATA_EXPOSURE]: The skill reads project-specific artifacts including spec.md, plan.md, tasks.md, and .specify/memory/constitution.md. This access is necessary for the stated goal of identifying inconsistencies and ambiguities across files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from markdown files (spec.md, plan.md, tasks.md).
  • Ingestion points: Files are loaded in Workflow Step 2.
  • Boundary markers: No explicit XML or character-based delimiters are used for the content.
  • Capability inventory: The skill is strictly read-only and its primary output is a markdown report, which limits the impact of potential injection.
  • Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:10 PM
Security Audit — agent-trust-hub — speckit-analyze