speckit-implement

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill executes a local prerequisite check script located at .specify/scripts/bash/check-prerequisites.sh and performs git operations (git rev-parse). While these are standard for environment validation, they represent a command execution surface that relies on the integrity of the local repository environment.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) as it directly translates instructions from repository files into implementation actions.
  • Ingestion points: The agent reads and parses tasks.md, plan.md, data-model.md, contracts/, research.md, and quickstart.md.
  • Boundary markers: Absent. There are no instructions to the agent to ignore or sanitize instructions embedded within these data files.
  • Capability inventory: High. The agent has the authority to create/modify files, update task lists, and initialize project configurations based on the input data.
  • Sanitization: Absent. The workflow lacks a validation step to ensure that implementation tasks do not contain malicious instructions meant to subvert the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM