Add SAFE-T1603 System-Prompt Disclosure#170
Open
VikranthKumar wants to merge 1 commit intosafe-agentic-framework:mainfrom
Open
Add SAFE-T1603 System-Prompt Disclosure#170VikranthKumar wants to merge 1 commit intosafe-agentic-framework:mainfrom
VikranthKumar wants to merge 1 commit intosafe-agentic-framework:mainfrom
Conversation
Signed-off-by: Vikranth Kumar Shivaa <srisnevisa@gmail.com>
| ) | ||
|
|
||
|
|
||
| class SystemPromptDisclosureDetector: |
Contributor
There was a problem hiding this comment.
Have you tested these on a real MCP connected to an LLM?
Since the MCP passes its information and details to the LLM to decide which tool to call, I think you need to update to more robust detection techniques.Relying on LLM calls and regex matching is not a reliable or perfect approach for this.
Kindly update
test_detection_rule.pyandtest-logs.json.
Collaborator
There was a problem hiding this comment.
@rockerritesh can you can contribute on this one.
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR adds SAFE-T1603: System-Prompt Disclosure to the SAFE-MCP framework, documenting how attackers can coerce an MCP-enabled assistant to leak hidden system/developer instructions and/or tool registry/schema details (e.g.,
inputSchema). This disclosure enables more reliable follow-on tool abuse and guardrail bypass.Type of Contribution
Checklist
git commit -s)Related Issues
New Technique