ai-slides

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data (topics, outlines, notes) to generate presentation content. This architecture creates an indirect prompt injection surface where malicious instructions within the source material could potentially hijack the generation logic.
  • Ingestion points: User-provided topic, outline, or notes (defined in SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the input data.
  • Capability inventory: Integration with office-mcp tools create_pptx and add_slide (SKILL.md).
  • Sanitization: No input validation or filtering of external content is mentioned or shown in the provided logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:17 AM