Applicant Screening

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow is to “screen these applications” (e.g., resumes/applications provided by others), and that free-form applicant text is ingested into the LLM context to evaluate requirements—i.e., outsider-authored resume/application content.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)