devexpress-xaf-filtering
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a potential vulnerability surface where dynamic filtering criteria (via
CriteriaOperator.Parse) could be built from untrusted data such as user input or external configuration. - Ingestion points: Specifically identifies that
CriteriaOperator.Parsemay receive strings from user input or configuration files (SKILL.md, references/criteria-syntax.md). - Boundary markers: The skill explicitly instructs the agent to use
?placeholders for parameterization and warns against string concatenation to prevent injection. - Capability inventory: The criteria strings are processed by
IObjectSpacemethods to execute queries against the application database. - Sanitization: Clear guidance is provided to use parameterized queries, which is the standard mitigation for this vector in XAF applications.
- [SAFE]: The skill recommends using official DevExpress MCP tools for documentation retrieval. These tools facilitate access to verified API references and do not involve unauthorized code execution or network exfiltration.
- [SAFE]: All NuGet packages (
DevExpress.Data,DevExpress.ExpressApp, etc.) and domains (docs.devexpress.com) identified in the skill are official vendor-owned assets, representing normal and expected functionality for this framework.
Audit Metadata