mlops-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection surface detected. 1. Ingestion points: userMessage in AiService.chat and jobDescription in JobAnalysisService.analyzeJob in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: AI provider network requests (Gemini, OpenAI, Groq), no shell or file system access. 4. Sanitization: Absent in templates.
Audit Metadata