m-scan
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to traverse and extract data from untrusted codebase files (CSS, HTML, JSX). This creates a surface for indirect prompt injection where malicious content inside the scanned files could attempt to influence the agent's behavior or poison the generated design profile.
- Ingestion points: Project codebase files including CSS, HTML, and JSX files.
- Boundary markers: None mentioned in the instructions to delimit untrusted content.
- Capability inventory: File system traversal and reading; writes output to a local file (.meridian.json).
- Sanitization: No explicit sanitization or validation steps are described for the data extracted from the source files.
Audit Metadata