speckit-implement

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh during its initialization workflow to validate prerequisites and parse configuration.
  • [COMMAND_EXECUTION]: It uses the git rev-parse --git-dir command to detect if the workspace is a Git repository, which guides the automatic generation of ignore files.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes multiple external markdown files (tasks.md, plan.md, etc.) to drive its implementation logic and code generation.
  • Ingestion points: specs/<feature>/tasks.md, plan.md, data-model.md, contracts/, research.md, and quickstart.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate task data from executable instructions.
  • Capability inventory: Includes executing local bash scripts, performing Git operations, and writing/modifying files throughout the repository.
  • Sanitization: The skill does not describe any validation or sanitization of the content within the markdown files before acting upon them.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — speckit-implement