The Agent Skills Directory

[SAFE]: The skill focuses on documentation and domain modeling workflows. No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized command execution were detected. The instructions are transparent and aligned with the stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it reads external content from the codebase and user input to generate documentation updates.
Ingestion points: The agent is instructed to read GLOSSARY.md, GLOSSARY-MAP.md, Architecture Decision Records (ADRs), and source code files within the src/ directory to verify domain terminology.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions potentially embedded in the analyzed code files.
Capability inventory: The skill's capabilities are limited to reading project files and writing or updating markdown documentation.
Sanitization: No specific sanitization or filtering logic is defined for processing content read from external codebase files.

domain-modeling