pptx-translation

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data which creates an attack surface for indirect prompt injection. 1. Ingestion points: Reads .pptx and JSON files via python_backend/generate_pptx.py. 2. Boundary markers: No delimiters or instructions to ignore embedded content are specified. 3. Capability inventory: Access to Bash, Write, and Edit tools with subprocess execution. 4. Sanitization: No validation or sanitization of slide content is mentioned.
  • [COMMAND_EXECUTION]: The agent uses the Bash tool to activate local virtual environments and execute internal Python scripts for file processing, which aligns with its primary purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references Supabase Storage and the Claude API (Anthropic), which are trusted platforms for storage and machine translation services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 04:17 PM