keynote-composer

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed entirely of natural language instructions (SOP) for an AI agent to generate text. It does not provide or call any external scripts, binaries, or command-line tools.
  • [SAFE]: No network operations, data exfiltration patterns, or sensitive file accesses were identified.
  • [SAFE]: No obfuscation (base64, hex, homoglyphs, or zero-width characters) was found in any of the files.
  • [SAFE]: The metadata (name, description, and license) is consistent with the provided functionality and does not contain deceptive patterns or prompt injections.
  • [SAFE]: While the skill processes user-supplied information to draft speeches, it lacks any high-risk capabilities (like file writing or network calls) that would make indirect prompt injection a concern.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM