skills/anbeime/skill/pptx-generator/Gen Agent Trust Hub

pptx-generator

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard, well-known Python libraries (python-pptx, pillow, openpyxl) for its core functionality. The scripts (json_validator.py, pptx_builder.py, pptx_validator.py) perform their tasks locally without any external network communication or unauthorized file system access.
  • [SAFE]: No obfuscation, Base64 encoding, or hidden URL patterns were detected in the source code or instructional content.
  • [SAFE]: Indirect Prompt Injection Analysis:
  • Ingestion points: The scripts ingest untrusted content from JSON files (e.g., ppt_data.json) which contain text for PPT slides.
  • Boundary markers: None identified; the skill treats all JSON content as literal data for the generated presentation.
  • Capability inventory: The skill is limited to file system writes for the output .pptx file. It lacks network capabilities or shell execution functionality that could be abused by malicious content in the JSON.
  • Sanitization: The skill uses standard JSON parsing which prevents structural confusion, although it does not sanitize the text content itself (which is typical for a document generation tool).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 01:20 AM
Security Audit — agent-trust-hub — pptx-generator