mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-03 22:19:27 +00:00
868416bfe0
* fix: add SSRF and path traversal protections CVE-2026-2286: validate_url blocks non-http/https schemes, private IPs, loopback, link-local, reserved addresses. Applied to 11 web tools. CVE-2026-2285: validate_path confines file access to the working directory. Applied to 7 file and directory tools. * fix: drop unused assignment from validate_url call * fix: DNS rebinding protection and allow_private flag Rewrite validated URLs to use the resolved IP, preventing DNS rebinding between validation and request time. SDK-based tools use pin_ip=False since they manage their own HTTP clients. Add allow_private flag for deployments that need internal network access. * fix: unify security utilities and restore RAG chokepoint validation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor: move validation to security/ package + address review comments - Move safe_path.py to crewai_tools/security/; add safe_url.py re-export - Keep utilities/safe_path.py as a backwards-compat shim - Update all 21 import sites to use crewai_tools.security.safe_path - files_compressor_tool: validate output_path (user-controlled) - serper_scrape_website_tool: call validate_url() before building payload - brightdata_unlocker: validate_url() already called without assignment (no-op fix) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor: move validation to security/ package, keep utilities/ as compat shim - security/safe_path.py is the canonical location for all validation - utilities/safe_path.py re-exports for backward compatibility - All tool imports already point to security.safe_path - All review comments already addressed in prior commits * fix: move validation outside try/except blocks, use correct directory validator Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: use resolved paths from validation to prevent symlink TOCTOU, remove unused safe_url.py --------- Co-authored-by: Alex <alex@crewai.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
OCR Tool
Description
This tool performs Optical Character Recognition (OCR) on images using supported LLMs. It can extract text from both local image files and images available via URLs. The tool leverages the LLM's vision capabilities to provide accurate text extraction from images.
Installation
Install the crewai_tools package
pip install 'crewai[tools]'
Supported LLMs
Any LLM that supports the vision feature should work. It must accept image_url as a user message.
The tool has been tested with:
- OpenAI's
gpt-4o - Gemini's
gemini/gemini-1.5-pro
Usage
In order to use the OCRTool, make sure your LLM supports the vision feature and the appropriate API key is set in the environment (e.g., OPENAI_API_KEY for OpenAI).
from crewai_tools import OCRTool
selected_llm = LLM(model="gpt-4o") # select your LLM, the tool has been tested with gpt-4o and gemini/gemini-1.5-pro
ocr_tool = OCRTool(llm=selected_llm)
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config["researcher"],
allow_delegation=False,
tools=[ocr_tool]
)
The tool accepts either a local file path or a URL to the image:
- For local files, provide the absolute or relative path
- For remote images, provide the complete URL starting with 'http' or 'https'