pdfcraft-compress-pdf
Warn
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration in
references/craft-command-evidence.jsonspecifies a binary download for the tool runtime from an external GitHub repository:https://github.com/storytold/pdfcraft/releases/download/v0.8.0/pdfcraft-0.8.0-windows-x64-portable.zip. - [REMOTE_CODE_EXECUTION]: The metadata identifies
pdfcraft-cli.exeas the executable to be run. Since this is downloaded from an external source and subsequently executed to perform PDF tasks, it represents a remote code execution vector. - [COMMAND_EXECUTION]: The skill provides instructions in
SKILL.mdto install related components using the commandnpx skills add full-aigc-skills/pdfcraft-skills --skill pdfcraft-editor. This refers to a vendor-provided resource by the authorfull-aigc-skills. - [INDIRECT_PROMPT_INJECTION]: The skill processes PDF files which are untrusted external data. This creates a surface for indirect prompt injection if the PDF content contains malicious instructions designed to be interpreted by the AI agent.
- Ingestion points: PDF file paths are ingested via the
doc_opentool as described inSKILL.mdandreferences/craft-methods.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content were found in the skill's logic to prevent the agent from following instructions found inside the PDFs.
- Capability inventory: The skill possesses file system access capabilities (read and write) through tools like
doc_open,doc_optimize, andpage_render. - Sanitization: The instructions do not mention any sanitization or validation of the text or metadata content extracted from the PDF files before processing.
Audit Metadata