frontend-slides
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local system commands (
open,xdg-open, orstart) to launch the generated HTML presentation in the user's default browser. It also invokespython3to run data extraction scripts for PowerPoint conversion. - [EXTERNAL_DOWNLOADS]: For PowerPoint conversion, the skill utilizes the
python-pptxlibrary. It may prompt the user to install this package viapipif it is not already available in the environment. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted content extracted from user-supplied PowerPoint files or pasted text.
- Ingestion points: Text and notes extracted from
.pptand.pptxfiles, as well as user-pasted presentation notes (defined in SKILL.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat extracted content as data only and ignore any embedded instructions.
- Capability inventory: The skill has the ability to execute shell commands for opening files and run python scripts via subprocess calls.
- Sanitization: There is no evidence of text sanitization or filtering for the extracted content, though the skill enforces strict structural and density constraints on the generated slides.
Audit Metadata