The Agent Skills Directory

[SAFE]: The skill is restricted to documentation management within the local repository environment. It lacks any capabilities for network communication, arbitrary command execution, or access to sensitive system credentials.
[INDIRECT_PROMPT_INJECTION]: The skill ingests project code and existing documentation to inform its domain modeling suggestions. While this ingestion surface could theoretically process malicious content, the skill's capabilities are limited to proposing and recording documentation updates, which prevents high-impact exploitation. Evidence: (1) Ingestion points: CONTEXT.md and project code files as referenced in SKILL.md; (2) Boundary markers: None; (3) Capability inventory: File-write operations limited to CONTEXT.md and docs/adr/ files; (4) Sanitization: None identified, but limited action scope mitigates risk.

domain-modeling