fix: replace eval() with safe AST evaluator in calculator template#5307
Open
xr843 wants to merge 1 commit intocrewAIInc:mainfrom
Open
fix: replace eval() with safe AST evaluator in calculator template#5307xr843 wants to merge 1 commit intocrewAIInc:mainfrom
xr843 wants to merge 1 commit intocrewAIInc:mainfrom
Conversation
The calculator tool example used eval() on unvalidated LLM input, enabling remote code execution. Replace with an AST-based evaluator that only allows arithmetic operations and numeric literals. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
xr843
force-pushed
the
fix/safe-eval-calculator
branch
from
2f8613e to
839d446
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #5056
eval()call in the Calculator tool example (AGENTS.mdline 773) with a safe AST-based arithmetic evaluatoreval()on unvalidated LLM output is a remote code execution (RCE) vulnerability — an adversarial prompt or malicious input can execute arbitrary Python codesafe_eval()function usesast.parse()and only allows numeric literals and arithmetic operators (+,-,*,/,**,%, unary-)Security Impact
Severity: High — Since this is a template that users copy into their projects, the vulnerable pattern propagates to every new crewAI project that uses the Calculator tool example.
Test plan
safe_eval("2 + 3 * 4")returns14.0safe_eval("__import__('os').system('whoami')")raisesValueError+,-,*,/,**,%🤖 Generated with Claude Code