Secure subprocess usage in bulk_generate_mad.py against command injection #6
+247
−4
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Outdated suggestions cannot be applied.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.
The script accepted unvalidated user input from YAML config files (
language,extractor_options) and passed it to subprocess calls, creating a command injection vulnerability.Changes
Input validation
VALID_LANGUAGESwhitelist for 9 supported CodeQL languages (cpp, csharp, go, java, javascript, python, ruby, rust, swift)validate_language()to reject languages outside the whitelistvalidate_extractor_options()to reject shell metacharacters:;&|<>\$(){}[]'"\n*`main()andbuild_database()to fail fastSubprocess hardening
shell=Falseto bothsubprocess.check_callinvocations--language, language) instead of string concatenation (--language={language})Documentation & testing
Example
Original prompt
This pull request was created as a result of the following prompt from Copilot chat.
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.