powerclaude
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a supporting framework and assets from the author's repository on GitHub (
cedanl/clidev-presentaties). It also installs standard industry libraries, such aspptxgenjsandpython-pptx, from official public registries. - [COMMAND_EXECUTION]: The skill automates environment setup and file rendering using various system commands. It uses
reg add(Windows) orfc-cache(Linux) ininstall-fonts.mjsto register fonts for the current user, and invokespowershell.exe,libreoffice, orpdftoppminrender.mjsto convert presentations into PDFs and PNG images for review. - [DYNAMIC_EXECUTION]: The build process involves dynamically importing a JavaScript specification file (
.deck.mjs) at runtime to define the presentation's structure and content, which involves dynamic loading from computed paths. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection when interacting with external data. Ingestion points: The
edit.pyscript reads and extracts text from existing.pptxfiles. Boundary markers: There are no explicit delimiters or instructions defined to isolate external slide content. Capability inventory: The skill has permissions to write files, execute shell commands, and perform dynamic imports. Sanitization: Text extracted from external presentations is not escaped or sanitized before being returned to the agent's context.
Audit Metadata