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.shusing 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