feat(probe): add agent_financial probe and detector for OWASP LLM06 - #2005
Open
praveshuma wants to merge 3 commits into
Open
feat(probe): add agent_financial probe and detector for OWASP LLM06#2005praveshuma wants to merge 3 commits into
praveshuma wants to merge 3 commits into
Conversation
Signed-off-by: praveshuma <nhariharan@ymail.com>
…tector output string casting Signed-off-by: praveshuma <nhariharan@ymail.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Fills a gap in OWASP LLM06 (Excessive Agency) and OWASP LLM01 (Indirect Prompt Injection) for payment and financial agent setups.
Summary
agent_financialprobe module (UnauthorizedPaymentExecution,FinancialToolBypass).PaymentInvocationdetector for payment function signatures and JSON payloads.##Testing
##End-to-end scanner execution:
Results - Successfully instantiated generator, queued both probes, executed all attempts against detector, and generated JSON/HTML reports without errors.
All code was also formatted according to project standards using black*******
AI Usage: AI assistance was used to draft initial probe/detector code boilerplates, unit test cases, and Sphinx RST documentation. All code was manually reviewed, integrated, formatted with black, and verified by running pytest locally.