frontend-slides
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external PowerPoint files and existing HTML presentations. This creates a surface where malicious instructions embedded in the input data could influence the agent's behavior during generation.
- Ingestion points: Content is extracted from user-supplied .pptx files and existing HTML presentations (SKILL.md Phase 0 and Phase 4).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the extracted data.
- Capability inventory: The skill allows file writing and execution of shell/Python scripts.
- Sanitization: There is no explicit requirement for the agent to sanitize or filter the extracted content before interpolation.
- [EXTERNAL_DOWNLOADS]: Presentations are configured to fetch font assets from trusted providers including Google Fonts and Fontshare (api.fontshare.com).
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands for opening browser windows and running content extraction scripts.
- [DYNAMIC_EXECUTION]: The agent is instructed to generate and run a Python script based on a provided template to handle PowerPoint content extraction (SKILL.md Phase 4.1).
Audit Metadata