e2e-auth-flow
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for automating tests that ingest untrusted data from external sources, specifically email testing services.
- Ingestion points: The registration test template retrieves content from external email services using patterns like
mailhog.getMessages({ to: email })inSKILL.md. - Boundary markers: The provided code snippets do not include explicit delimiters or warnings for the agent to ignore instructions embedded within the retrieved emails.
- Capability inventory: The testing templates utilize capabilities including network requests (
cy.request,page.goto), browser state modification (storageState), and database interactions (db.findByEmail,db.createPasswordResetToken). - Sanitization: There is no evidence of sanitization or filtering of external content before it is processed or evaluated within the test context.
- [SAFE]: The skill is primarily educational, providing templates and best practices for developers. It includes proactive security advice, such as warning against hardcoding credentials and recommending the verification of server-side session destruction during logout tests.
Audit Metadata