architecture-blueprint-generator
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily focused on static analysis of code for documentation purposes. No evidence of malicious command execution, unauthorized network requests, or hardcoded credential exposure was found.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it analyzes untrusted codebase data. * Ingestion points: Project and configuration files, source code, and package dependencies (SKILL.md sections 1 and 7). * Boundary markers: None identified; the AI is instructed to analyze the code directly within its reasoning context. * Capability inventory: The skill generates text/Markdown documentation; it lacks capabilities for file-system modification, network exfiltration, or shell execution. * Sanitization: There is no explicit sanitization step for the code content before it is summarized into the blueprint.
Audit Metadata