b2c-controllers
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing untrusted external data from HTTP requests (e.g.,
req.querystring,req.form,request.httpParameterMap) inSKILL.md,references/SFRA-PATTERNS.md, andreferences/CLASSIC-PATTERNS.md. While this represents a potential attack surface for indirect prompt injection at runtime in the developed code, the skill provides appropriate security controls such as CSRF validation and authentication middleware to mitigate these risks. This behavior is fundamental to the skill's primary purpose of teaching web development. - Ingestion points: Handlers for query parameters and form data are described in
SKILL.mdand reference files. - Boundary markers: The documentation demonstrates standard request/response handling; it does not explicitly define agent-level delimiters but follows platform-standard isolation.
- Capability inventory: No dangerous system calls, network operations, or file-system writes are present in the skill content itself.
- Sanitization: The skill explicitly documents and recommends the use of security middleware for CSRF protection (
csrfProtection.validateAjaxRequest) and authentication (userLoggedIn.validateLoggedIn).
Audit Metadata