The Agent Skills Directory

[SAFE]: The skill facilitates domain modeling by managing documentation files such as CONTEXT.md and Architectural Decision Records (ADRs). It does not perform any high-risk operations such as remote code execution, network requests, or sensitive credential access.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes data from project source code and context files.
Ingestion points: The skill reads CONTEXT.md, CONTEXT-MAP.md, project source code in src/, and agent-specific knowledge from knowledge-vault.md.
Boundary markers: No explicit boundary markers or delimiters are defined in the instructions to distinguish between domain data and potential embedded instructions.
Capability inventory: The skill is limited to reading files and writing Markdown content to specific documentation paths (CONTEXT.md, docs/adr/*.md).
Sanitization: No specific sanitization or filtering of external content is mentioned.
Note: This surface is inherent to the skill's primary function of synchronizing documentation with code. Given that the skill lacks execution privileges or network access, this surface does not represent a significant security threat.

domain-modeling