gpt-image-slide

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including user-provided "source files" and "reference slide images," which creates a surface for indirect prompt injection.
  • Ingestion points: The workflow ingests information from user-supplied visual references and source files (SKILL.md).
  • Capability inventory: The skill performs file system writes to the workspace (creating DESIGN.md, slide_plan.json, slide_prompts.json, and .png images) and invokes image generation tools.
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded within the processed user files.
  • Sanitization: No sanitization or validation steps for the input data are defined within the orchestration logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 05:51 AM
Security Audit — agent-trust-hub — gpt-image-slide