Skills
Navigate
skills/thatrebeccarae/claude-marketing/pro-deck-builder/Gen Agent Trust Hub

pro-deck-builder

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to discover installed font families (fc-list) and locate logo assets (find) across common user-accessible directories like Desktop and Downloads. It also executes local Python scripts for auxiliary tasks such as thumbnail generation and PDF conversion via LibreOffice.
  • [EXTERNAL_DOWNLOADS]: Installation instructions require cloning the author's GitHub repository and installing standard, well-known libraries from NPM and PyPI (e.g., pptxgenjs, react-icons, markitdown). These resources are consistent with the skill's purpose and the author's identified environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses the capability to read and extract content from existing PowerPoint presentations via the markitdown tool.
  • Ingestion points: markitdown execution on user-provided .pptx files as described in SKILL.md.
  • Boundary markers: Absent; instructions do not explicitly bound or isolate processed content.
  • Capability inventory: The skill can write files (pres.writeFile) and execute shell commands for design tasks.
  • Sanitization: Absent; the skill relies on the underlying LLM's safety guardrails when processing extracted text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — pro-deck-builder