Applicant Screening

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: This skill contains no executable scripts or binary files, consisting entirely of markdown instructions and templates for HR screening.
  • [SAFE]: No malicious code or direct prompt injection attempts were found. The skill functions as intended for candidate evaluation.
  • [PROMPT_INJECTION]: The skill processes untrusted resume data, which creates an indirect prompt injection surface. 1. Ingestion points: Resumes via 'extract_text_from_pdf' and 'extract_text_from_docx'. 2. Boundary markers: Absent. 3. Capability inventory: Limited to analysis and report formatting. 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM