The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies and processes information from the project's source code and documentation, which constitutes an ingestion surface for potentially untrusted data.
Ingestion points: The agent is instructed to analyze user input, existing GLOSSARY.md files, and project source code (e.g., in the src/ directory) to verify terminology and implementation alignment.
Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are provided for the analysis of codebase content.
Capability inventory: The skill directs the agent to create and update markdown files (GLOSSARY.md, ADRs) based on its findings.
Sanitization: There are no explicit requirements for sanitizing or escaping content retrieved from the codebase before it is incorporated into project documentation.
[NO_CODE]: The skill consists of instructional markdown files and configuration metadata. It does not include any Python, JavaScript, or shell scripts for execution.
[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill's behavior is consistent with its stated purpose of domain modeling and documentation management.

domain-modeling