pptx-toolkit
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external
.pptxfiles. While the script primarily calculates metrics, it extracts text from slides to determine word counts. There is a minimal surface for indirect prompt injection if the AI agent subsequently reviews the extracted text or tool results containing slide content. However, the current tool only outputs metadata and counts, which significantly limits the attack surface. - Ingestion points:
scripts/pptx_auditor.pyreads slide XML files from the.pptxZIP archive. - Boundary markers: Absent in the tool output.
- Capability inventory: No network access, subprocess execution, or file-write capabilities were identified in the script.
- Sanitization: The script performs basic whitespace stripping for word counting but does not sanitize text for LLM ingestion.
Audit Metadata