legal-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a static document generator, creating HTML files with embedded SVG content for litigation analysis and contract review. Its behavior is confined to data visualization and does not involve unauthorized access to system resources, sensitive files, or network services.
- [EXTERNAL_DOWNLOADS]: The skill includes a reference to the Google Fonts API to fetch the 'Inter' typeface for styling the generated diagrams. This is a standard and neutral use of a well-known service for delivering web assets and does not involve executable code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data, such as case details and evidence summaries, and interpolates these values into an HTML template. This establishes a vulnerability surface for indirect prompt injection where malicious input could attempt to influence the agent's output. However, the impact is mitigated by the skill's specific purpose of generating static visual content, which lacks the capability for dynamic code execution or privilege escalation.
Audit Metadata