skills/mukul975/anthropic-cybersecurity-skills/detecting-ai-model-prompt-injection-attacks/Gen Agent Trust Hub
detecting-ai-model-prompt-injection-attacks
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a legitimate security utility designed to analyze and classify potential prompt injection payloads. All inputs are evaluated locally via defined regular expressions, text structure scoring, and local transformer models.
- [EXTERNAL_DOWNLOADS]: The skill specifies a dependency on a machine learning model (
protectai/deberta-v3-base-prompt-injection-v2) hosted on the Hugging Face Hub. This model is downloaded dynamically during the first run using the standard Hugging Facetransformerspipeline. This is standard functionality for model-based sequence classification utilities and targets a well-known technological service infrastructure.
Audit Metadata