ppt-keynote

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill treats the remainder of the user's message as a brief for external tool processing, creating a surface for indirect prompt injection.
  • Ingestion point: SKILL.md instructs the agent to "Treat the rest of the user's message as the brief."
  • Boundary markers: The skill instructions lack explicit delimiters or warnings to ignore embedded instructions within the user-provided content.
  • Capability inventory: The skill utilizes tools like prepare_open_design_brief, list_open_design_design_systems, and register_open_design_artifact, along with file-editing capabilities.
  • Sanitization: There are no instructions provided to sanitize, validate, or escape the user's message before it is passed to the design brief tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 08:53 AM