umbraco-ufm-component
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill defines a workflow for creating components that process untrusted data from markdown tokens.
- Ingestion points:
token.textparameter in therendermethod of the generated components inSKILL.md. - Boundary markers: Absent; the logic assumes the markdown token content is safe for direct rendering.
- Capability inventory: Uses the
Writetool to generate and persist UI components in the Umbraco CMS. - Sanitization: Examples use direct string interpolation (e.g.,
${token.text}) into HTML strings without escaping. Although the 'Best Practices' section mentions escaping user input, the provided implementation templates are insecure.
Audit Metadata