gpt-slide-plan

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for role-playing as a presentation strategist and does not perform any risky operations or network communication. It strictly adheres to generating a structured JSON output based on provided documents.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content and a local DESIGN.md file. While it lacks explicit boundary markers or instructions to ignore commands within those documents, the risk is negligible as the skill has no access to sensitive tools, network resources, or command execution capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 06:07 AM
Security Audit — agent-trust-hub — gpt-slide-plan