The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and a template file. It does not define any allowed-tools or scripts, meaning it lacks the capability to perform restricted operations such as network calls or shell command execution.
[NO_CODE]: The provided files (SKILL.md and impact-template.md) contain only prose instructions and structured templates. There are no Python scripts, Node.js modules, or other executable artifacts included in the skill.
[INDIRECT_PROMPT_INJECTION]: Although the skill is designed to process external data (software requirements and invariants), it is not vulnerable to exploitation because it possesses no actionable capabilities (like network access or file system modification) that could be abused via malicious input. It functions solely as a reasoning and documentation aid.

domain-impact-analysis