The Agent Skills Directory

[SAFE]: The skill facilitates domain modeling and architectural documentation. It manages project-specific glossaries in CONTEXT.md and decision records in docs/adr/. The analysis found no evidence of credential theft, remote code execution, obfuscation, or persistence mechanisms. All operations are limited to standard file system interactions within the development environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from project source code and user input to generate documentation, which is its primary intended function.
Ingestion points: The skill reads source code from the src/ directory and terminology provided by the user during dialogue.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the source code it reads.
Capability inventory: The skill is limited to reading local project files and writing to markdown-based documentation files. It has no network capabilities, privilege escalation paths, or execution tools.
Sanitization: There are no explicit sanitization or filtering steps mentioned for the data processed from the source files before it is used to update the documentation.

domain-modeling