doc-to-everything
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external PDF files, creating a surface where malicious instructions embedded in documents could potentially affect the extraction workflow.
- Ingestion points: The skill reads user-supplied PDF files at multiple stages in
SKILL.md(Steps 3, 4, 5, and 6). - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the tools processing the document text.
- Capability inventory: The skill executes several shell commands (
ocr-scanned-pdf,pdf-to-markdown,chunk-markdown,extract-tables) and performs file system write operations. - Sanitization: There is no evidence of sanitization or filtering applied to the document content before it is processed by the pipeline tools.
- [COMMAND_EXECUTION]: The workflow involves executing a series of CLI tools to handle OCR and document conversion. These actions are directly tied to the primary functionality of the skill.
Audit Metadata