The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill is a productivity tool for domain-driven design and documentation maintenance.
[DATA_EXPOSURE]: The skill instructions involve reading existing repository files such as CONTEXT.md and ADR files. This behavior is the primary intended purpose of the skill and does not target sensitive system directories or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest and analyze content from the local codebase, which is a common pattern for development assistants.
Ingestion points: The agent is instructed in SKILL.md to "explore the codebase" and look for documentation.
Boundary markers: No specific delimiters or warnings are used when reading file content.
Capability inventory: The skill can create and update documentation files (CONTEXT.md, ADRs). It does not have access to network tools or arbitrary command execution.
Sanitization: No explicit sanitization or filtering of codebase content is defined. The risk remains low as the agent's actions are restricted to documentation management.

domain-model