meridian-design
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its design analysis workflow.
- Ingestion points: The skill reads project files (CSS, HTML, etc.) during the
/m-scanprocess to build a.meridian.jsonprofile. - Boundary markers: There are no instructions defining delimiters or warnings to ignore malicious instructions that might be embedded in the analyzed code comments or content.
- Capability inventory: The agent is instructed to write CSS and provide design recommendations based on the generated profile.
- Sanitization: No explicit sanitization or validation logic is provided to filter the content of ingested files before they are used to guide the agent's behavior.
Audit Metadata