arc42-documentation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read local project files and incorporate their content into a structured documentation template.
  • Ingestion points: The skill reads docs/spec.md, docs/features/, and adr-*.md files to gather architectural information.
  • Boundary markers: There are no explicit instructions to the agent to treat ingested data as untrusted or to use specific delimiters when processing this data.
  • Capability inventory: The skill has the ability to create and edit files using the edit/ toolset and can execute git commands for committing changes.
  • Sanitization: No explicit sanitization or filtering of the content read from project files is described before it is formatted into the arc42 template.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official and well-known resources for software architecture documentation.
  • References are provided to the official arc42 website (arc42.org), their documentation portal (docs.arc42.org), and their template repository on GitHub.
  • The skill also references recognized industry standards such as the iSAQB curriculum and the C4 model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:36 PM