pdfcraft-ocr-scans
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external binaries and model files for the PdfCraft engine.
- Evidence:
references/craft-command-evidence.jsonpoints to a portable Windows executable hosted atgithub.com/storytold/pdfcraft. - Evidence:
references/ocr-models.jsoncontains URLs for.rtenmodels hosted onocrs-models.s3-accelerate.amazonaws.com. - Note: All downloads are accompanied by SHA256 hashes for integrity verification.
- [DYNAMIC_EXECUTION]: The skill uses a CLI runner to execute task sequences defined in JSON format.
- Evidence:
references/craft-methods.mddescribes executingpdfcraft-cli run --script steps.json, wheresteps.jsondefines a sequence of tool calls. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing untrusted document content.
- Ingestion points: Document data enters via
doc_openandocr_recognizeas defined inreferences/craft-command-evidence.json. - Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the OCR'd text during extraction.
- Capability inventory: The skill can perform file system writes (
doc_save) and execute local CLI commands. - Sanitization: There is no evidence of sanitization or filtering of the text extracted from the PDF before it is returned to the agent context.
- [COMMAND_EXECUTION]: The instructions involve executing local CLI tools and managing node packages.
- Evidence:
SKILL.mdsuggests installing a related skill vianpx skills add full-aigc-skills/pdfcraft-skills. - Evidence:
references/craft-methods.mddetails usage ofpdfcraft-clifor processing documents.
Audit Metadata