ln-72-current-architecture-documenter
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data from the repository (source code, manifests, and configuration files) to generate architecture documentation, creating a vulnerability surface.
- Ingestion points: The skill instructions in
SKILL.mdrequire the agent to read repository manifests, CI configurations, source code symbols, Infrastructure as Code (IaC) files, and existing documentation. - Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores natural language instructions that might be embedded within the source code or comments it analyzes.
- Capability inventory: The skill utilizes file system reads, Git status/branch commands, and has the capability to write or patch documentation files (defaulting to
docs/architecture/current-state.md). - Sanitization: No specific sanitization, validation, or filtering of the ingested external content is mentioned before the information is processed and written to the output document.
Audit Metadata