The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and a basic YAML configuration file. It does not contain any executable scripts (Python, JavaScript, Shell, etc.) that could perform operations on the host system or network.
[DATA_EXPOSURE]: The skill guides the agent to read and write project documentation files (CONTEXT.md, ADR files). These operations are restricted to the local repository and the defined purpose of architectural documentation. No exfiltration patterns or sensitive file access (e.g., .env, SSH keys) were detected.
[PROMPT_INJECTION]: The instructions contain standard behavioral guidelines (e.g., 'Actively build and sharpen...', 'Challenge fuzzy language'). There are no attempts to override safety filters, bypass system prompts, or implement jailbreak-style logic.

domain-modeling