architecture-diagram
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- Project Analysis and File Access: The skill analyzes various build and configuration files, such as
pom.xml,package.json, and.env, to identify a project's technology stack and data patterns. While these files can contain sensitive information, the skill's purpose is to extract high-level architectural details for documentation. - Local File System Writing: The analysis results are saved to a specific path in the local project repository:
.github/modernize/assessment/engines/facts/architecture-diagram.md. This is a routine operation for generating assessment reports. - Indirect Prompt Injection Surface: Because the skill processes untrusted project files (source code and configuration) to generate descriptions, it possesses an indirect prompt injection surface. An attacker could potentially embed instructions within code comments or configuration values that might influence the generated diagram or textual explanations, though the impact is limited to the documentation output.
- Absence of Network Operations: There are no instructions or commands within the skill to perform network requests, exfiltrate data to remote servers, or download external scripts, which significantly reduces the risk profile.
Audit Metadata