The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill uses the Bash tool to execute TDD cycles and run local project tests such as npm run test. These actions are restricted to the local environment and are essential to the framework's stated purpose of feature development.
[PROMPT_INJECTION] (LOW): This finding identifies a surface for Indirect Prompt Injection (Category 8). The skill reads and acts upon external data sources that could be controlled by an attacker.
Ingestion points: Untrusted data enters the agent context through the specs/ directory and the existing codebase via Read, Glob, and Grep tools.
Boundary markers: Absent. There are no delimiters or specific instructions to the agent to ignore executable instructions found within the specification requirements.
Capability inventory: The skill has significant capabilities, including Bash command execution and the ability to Write or Edit files across the project.
Sanitization: Absent. The skill is designed to faithfully implement requirements found in the spec files without sanitizing the input for instructional overrides.

spec-driven-dev