improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs architectural analysis on the local codebase. It reads project documentation and source code to suggest improvements and manages local architecture records such as ADRs and context files.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted codebase content during exploration. Ingestion point: codebase files accessed via subagent exploration (SKILL.md). Boundary markers: None. Capability inventory: tool-based exploration and modification of documentation files (SKILL.md). Sanitization: None. Malicious instructions embedded in the analyzed code or documentation could influence the agent's behavior. This risk is inherent to the skill's primary function of code analysis and is mitigated by using it on trusted codebases.
Audit Metadata