scorecard-matrix
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from SharePoint lists, CSV tables, and chat input to generate a self-contained HTML scorecard. The lack of explicit sanitization or escaping rules for this data before it is rendered into the HTML document presents a vulnerability surface for indirect prompt injection or Cross-Site Scripting (XSS).
- Ingestion points: In SKILL.md (Step 1), the skill is instructed to parse SharePoint lists, tables, or CSV data provided by the user.
- Boundary markers: There are no instructions to use delimiters or security-focused boundary markers to isolate user-provided text from the rest of the report instructions.
- Capability inventory: The skill generates a full HTML file based on the assets/scorecard-matrix-template.html template (Step 6).
- Sanitization: The instructions do not specify any validation, escaping, or sanitization of the user-provided data before it is interpolated into the HTML template placeholders.
Audit Metadata