improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to analyze software architecture and assist with documentation. It does not contain suspicious commands, network operations, or obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase and documentation files. (1) Ingestion points: Reads files in
docs/adr/,CONTEXT.md, and general codebase files via the Explore agent inSKILL.md. (2) Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. (3) Capability inventory: The skill can read/write documentation files (CONTEXT.md, ADRs) and spawn sub-agents for analysis as described inSKILL.mdandINTERFACE-DESIGN.md. (4) Sanitization: No sanitization of ingested content is documented. This ingestion surface is typical for architecture analysis tools and is considered safe in this context.
Audit Metadata