The Agent Skills Directory

[SAFE]: The skill focuses on analyzing local architectural documentation using standard file access tools (Read, Glob, Grep). It does not perform network operations, execute arbitrary code, or access sensitive system configuration files.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading user-provided ADRs and review files in the .architecture/ directory. While these files could contain malicious instructions, the skill's capabilities are limited to local read-only operations, and it does not have the ability to execute commands or exfiltrate data, neutralizing the threat. Ingestion points: files in .architecture/decisions/adrs/ and .architecture/reviews/. Capabilities: Read, Glob, Grep on local paths. Sanitization: Not explicitly identified.

architecture-status