kdp-cover-wrap
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts (
build-cover.pyandkdp-package.py) via shell commands to automate the cover generation process and perform dimension validation. - [INDIRECT_PROMPT_INJECTION]: The skill uses
pdfinfoto extract page counts and metadata from interior PDF files. This creates a vulnerability surface where a maliciously crafted PDF with injected metadata could influence the agent's behavior during processing. - [DYNAMIC_EXECUTION]: Utilizes environment variables (e.g.,
${CLAUDE_PLUGIN_ROOT}) to resolve paths for script execution, which is a common pattern for skill-based tool invocation.
Audit Metadata