powerpoint
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external PowerPoint files, creating a surface where instructions embedded in slides or notes could influence agent behavior.
- Ingestion points: scripts/pptx_read.py parses and extracts text, table data, and speaker notes from .pptx files.
- Boundary markers: Extracted content is returned to the agent context without explicit delimiters or warnings.
- Capability inventory: The skill can read/write files and execute system commands for rendering.
- Sanitization: Content is processed as raw text without specific filtering for prompt instructions.
- [COMMAND_EXECUTION]: The skill executes system binaries for slide rendering.
- Evidence: scripts/pptx_render.py invokes soffice, pdftoppm, and pdftocairo via subprocess.run. It uses a secure list-based argument pattern to prevent shell injection and relies on established productivity utilities for their intended purpose.
Audit Metadata