Add LLM prompt injection detection rule (system prompt leakage)#1
Open
kamalkalwa wants to merge 1 commit intoEscape-Technologies:mainfrom
Open
Add LLM prompt injection detection rule (system prompt leakage)#1kamalkalwa wants to merge 1 commit intoEscape-Technologies:mainfrom
kamalkalwa wants to merge 1 commit intoEscape-Technologies:mainfrom
Conversation
Adds a prompt injection rule under vulnerabilities/prompt_injection/ that tests string fields for system prompt extraction attacks. The rule sends injection payloads via request.object mutations and detects leakage by matching response text against patterns like raw template tokens (<<SYS>>, [INST], <|system|>), instruction disclosure phrases, and debug mode acknowledgments. Maps to OWASP LLM Top 10 - LLM01 (Prompt Injection) and CWE-77.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a new vulnerability rule for detecting LLM system prompt leakage via prompt injection.
Location:
vulnerabilities/prompt_injection/system_prompt_leakage.yamlWhat it does:
<<SYS>>,[INST],<|system|>), instruction disclosure phrases, and debug mode acknowledgmentsCompliance mapping: OWASP LLM Top 10 - LLM01 (Prompt Injection), CWE-77
Why: With more APIs wrapping LLM backends, prompt injection is becoming one of the most common API security issues. Didn't see an existing rule covering this.