frontend-slides
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes platform-specific shell commands (
open,xdg-open,start) to launch the generated HTML presentations in the user's browser. - [EXTERNAL_DOWNLOADS]: The skill encourages the installation of the
python-pptxlibrary viapython3for file conversion and fetches web fonts from Google Fonts and Fontshare. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external PowerPoint files and user notes without explicit sanitization or boundary markers.
- Ingestion points: The skill reads content from
.pptand.pptxfiles during conversion and accepts raw text/notes from the user for slide generation. - Boundary markers: Absent. There are no instructions provided to the agent to treat external content as data only or to ignore embedded commands.
- Capability inventory: The agent utilizes
python3for data extraction and system-level shell commands to interact with the file system and browser. - Sanitization: Absent. No validation or filtering is performed on the data ingested from external presentation files before it is processed by the AI.
Audit Metadata