The Agent Skills Directory

[SAFE]: The skill's primary function is to guide the agent in maintaining clear domain terminology and architectural records. All operations are limited to reading and writing markdown documentation within the repository structure. No evidence of malicious intent, obfuscation, or data exfiltration was found.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository to perform its tasks, creating a theoretical attack surface for indirect prompt injection.
Ingestion points: Reads CONTEXT.md, CONTEXT-MAP.md, KNOWLEDGE.md, and source code to identify domain terms and architectural context.
Boundary markers: None; the skill processes repository files as trusted context for documentation updates.
Capability inventory: Limited to reading and writing markdown files within the project directory.
Sanitization: No explicit sanitization or filtering of ingested data is described.
Risk Assessment: Given the restricted capability set (documentation writing only) and absence of network or execution tools, this surface does not pose a significant security risk.

domain-modeling