pptx-manipulation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as presentation outlines and markdown content to generate slides. It lacks explicit boundary markers or sanitization to prevent embedded malicious instructions from affecting agent behavior. Ingestion points: User-provided slide outlines and markdown content referenced in SKILL.md. Capability inventory: Generation and execution of Python code using python-pptx. Boundary markers: Absent. Sanitization: Absent.
- [DYNAMIC_EXECUTION]: The skill generates and executes Python code at runtime to manipulate presentations, which is an inherent part of its functionality but represents a dynamic execution pattern.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the python-pptx package, which is a well-known library for presentation manipulation.
Audit Metadata