Add SAFE-T1112 Sampling Request Abuse#186
Open
saxena-gaurav wants to merge 1 commit intosafe-agentic-framework:mainfrom
Open
Add SAFE-T1112 Sampling Request Abuse#186saxena-gaurav wants to merge 1 commit intosafe-agentic-framework:mainfrom
saxena-gaurav wants to merge 1 commit intosafe-agentic-framework:mainfrom
Conversation
Signed-off-by: Gaurav Saxena <gauravsaxena@Gauravs-MacBook-Air.local>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a new Execution technique, SAFE-T1112: Sampling Request Abuse, to document abuse of the MCP
sampling/createMessageprimitive and tool-enabled sampling flows.Changes
techniques/SAFE-T1112/README.mdtechniques/SAFE-T1112/detection-rule.ymltechniques/SAFE-T1112/test-logs.jsontechniques/SAFE-T1112/test_detection_rule.pyWhy
This technique is not currently represented in the SAFE-MCP Execution catalog. It is distinct from broad prompt injection because the trust boundary under abuse is the MCP sampling primitive itself, including nested model calls, user approval flows, and tool-enabled sampling.
Validation
python3 techniques/SAFE-T1112/test_detection_rule.py