senior-ml-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill documentation indicates capabilities for RAG and LLM system development, which are surfaces for indirect prompt injection. 1. Ingestion points: Untrusted data ingestion via scripts/rag_system_builder.py and scripts/model_deployment_pipeline.py. 2. Boundary markers: None identified. 3. Capability inventory: Subprocess execution of local Python scripts, container management, and orchestration tools. 4. Sanitization: Best practices for input validation are not specified in the skill definition.
Audit Metadata