doc-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The INSTALL.md file provides instructions for installing the skill using npx skills add RuralNative/RuralNative-SKILLS and by cloning the source repository from https://github.com/RuralNative/RuralNative-SKILLS.git. Both methods target repositories and resources associated with the skill's author.
  • [COMMAND_EXECUTION]: The documentation harness described in reference/harness.md utilizes shell commands such as git status --porcelain to verify the freshness of documentation against the current state of the version-controlled codebase.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the user's codebase, creating a surface for potential indirect prompt injection.
  • Ingestion points: The skill walks the codebase and reads existing documentation files during the Establish (SKILL.md, Branch A Step 3) and Audit (SKILL.md, Branch B Step 1) phases.
  • Boundary markers: No specific delimiters or instructions to ignore embedded malicious content are defined within the skill's templates or processing rules.
  • Capability inventory: The skill is granted file-writing capabilities to create and update the documentation tree, including indices, ADRs, and seam leaf documents (SKILL.md, Branch A Step 4).
  • Sanitization: The skill does not specify sanitization or validation routines for the data extracted from the codebase before it is incorporated into generated documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:15 AM