High-risk tools in Document Parser
3 of the 5 tools in Document Parser are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
parse_image_textExecute 3/5Perform OCR on images to extract text with confidence scores. Supports screenshots, scanned documents, photos of text. Returns structured text with confidence metrics. Essential...
-
parse_pdfExecute 4/5Extract text, tables, and metadata from PDF files with layout preservation. Perfect for agents processing reports, invoices, contracts, research papers. Handles multi-page docum...
-
summarize_documentExecute 3/5Parse any document and generate a structured summary with configurable detail level. Extracts key information, main points, and metadata. Perfect for agents that need document o...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on Document Parser
Enforce policy on Document Parser
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init