powerpoint-ppt

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external text for slide content without explicit sanitization or boundary markers, which presents a theoretical injection surface during automated presentation building.\n
  • Ingestion points: Slide text, titles, and bullet points processed in scripts/ppt-automation.py and examples/presentation-examples.md.\n
  • Capability inventory: Slide creation, text placeholder population, and image management via MCP tools or python-pptx.\n
  • Boundary markers: None present in the content processing instructions.\n
  • Sanitization: No explicit content filtering for interpolated slide data.\n- [SAFE]: The helper script scripts/ppt-automation.py is a legitimate tool for structuring presentation data. It does not perform dangerous network operations, file system access outside of its scope, or use dynamic execution functions like eval or exec.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:16 AM
Security Audit — agent-trust-hub — powerpoint-ppt