blip-2-vision-language

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documentation includes examples of processing external image and text data using vision-language models, which is an inherent attack surface for indirect prompt injection.
  • Ingestion points: The skill demonstrates model inference using Blip2Processor and load_model_and_preprocess which take local image files (e.g., 'photo.jpg') and user-provided text questions as input in SKILL.md and references/advanced-usage.md.
  • Boundary markers: The provided code samples do not demonstrate the use of boundary markers or instructions to isolate potentially malicious embedded content within the inputs.
  • Capability inventory: The skill showcases inference, batch processing, feature extraction, and fine-tuning capabilities. One integration example uses these capabilities to build a searchable index of image features.
  • Sanitization: The documentation does not provide examples of sanitizing or validating ingested visual or textual content prior to model processing.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading pre-trained models and cloning external code repositories.
  • Evidence: The documentation specifies fetching model weights from the official Salesforce organization on HuggingFace and cloning the LAVIS repository from Salesforce's GitHub in SKILL.md and references/troubleshooting.md. These represent standard operations using well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:07 PM
Security Audit — agent-trust-hub — blip-2-vision-language