dspy-adapters-multimodal

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and examples for configuring DSPy adapters and handling media files. It does not perform unauthorized network operations, execute remote code, or expose sensitive data.
  • [PROMPT_INJECTION]: The skill describes how to handle external media which represents a potential surface for indirect prompt injection when processing untrusted data. 1. Ingestion points: Data loaded via dspy.Image, dspy.Audio, and dspy.File primitives as shown in SKILL.md examples. 2. Boundary markers: Not specified in the documentation samples. 3. Capability inventory: Tool access includes Read, Write, Glob, and Grep. 4. Sanitization: No specific validation logic is included in the usage examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:02 PM
Security Audit — agent-trust-hub — dspy-adapters-multimodal