gpt-slide-prompt

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and a JSON output schema. It does not include any scripts (.py, .js, .sh) or executable binaries.
  • [SAFE]: No network operations (e.g., curl, wget, fetch) or remote code downloads are present in the instructions.
  • [SAFE]: The skill does not attempt to access sensitive file paths (e.g., .ssh, .aws, .env) or hardcode any credentials.
  • [SAFE]: Analysis for obfuscation techniques (Base64, zero-width characters, homoglyphs) returned no findings.
  • [SAFE]: The skill ingests external data (DESIGN.md, slide_plan.json) to generate prompts, which is a standard transformation task. While this represents a surface for indirect prompt injection, the skill's lack of executable capabilities (only outputting JSON) renders this risk negligible in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 06:07 AM
Security Audit — agent-trust-hub — gpt-slide-prompt