frontend-slides

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses platform-specific commands such as open, xdg-open, and start to launch the generated HTML presentations in the user's default browser. This is an intended convenience feature for the user.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the standard python-pptx library for PowerPoint conversion. It includes logic in SKILL.md to check for its presence and may prompt the user to install it from a package registry if necessary.\n- [PROMPT_INJECTION]: The skill processes user-supplied content and PowerPoint files in SKILL.md, which creates an indirect prompt injection surface. While the skill lacks explicit boundary markers or sanitization for this data, its capabilities are restricted to content extraction and template generation, minimizing the risk of harmful instruction execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:09 AM
Security Audit — agent-trust-hub — frontend-slides