keynote-composer

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No suspicious patterns or malicious behaviors were detected in the skill's instructions or metadata. The workflow is focused entirely on professional writing tasks.
  • [NO_CODE]: The skill consists entirely of markdown instructions and does not include scripts, executables, or external dependencies, significantly reducing the attack surface.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics and occasion details to generate content. While this creates a surface for indirect prompt injection (where a user might provide malicious instructions as 'speech topics'), the skill lacks the capabilities—such as network access, file system access, or command execution—necessary for such an injection to result in a security breach.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 08:58 AM