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/, andadr-*.mdfiles 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 executegitcommands 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