-
Notifications
You must be signed in to change notification settings - Fork 1
Document prompt injection risks and mitigations #41
Copy link
Copy link
Open
Labels
aiAI generation, prompts, or model integrationAI generation, prompts, or model integrationdocumentationDocumentation improvementsDocumentation improvementshighComplex issue, suggested 200-point complexityComplex issue, suggested 200-point complexitysecuritySecurity review or hardeningSecurity review or hardeningwave-readyReady for Drips Wave submissionReady for Drips Wave submission
Description
Metadata
Metadata
Assignees
Labels
aiAI generation, prompts, or model integrationAI generation, prompts, or model integrationdocumentationDocumentation improvementsDocumentation improvementshighComplex issue, suggested 200-point complexityComplex issue, suggested 200-point complexitysecuritySecurity review or hardeningSecurity review or hardeningwave-readyReady for Drips Wave submissionReady for Drips Wave submission
Type
Fields
Give feedbackNo fields configured for issues without a type.
Document prompt injection risks and mitigations
Repository:
PolymorphicAI/study-copilotSuggested Labels: documentation, ai, security, high, wave-ready
Suggested Complexity: High / 200 points
Summary
Document prompt injection risks for user-provided notes, PDFs, and topics.
Why This Matters
User-supplied study materials may contain instructions that affect AI output.
Tasks
Acceptance Criteria
Suggested Complexity
High / 200 points
Suggested Labels
documentation, ai, security, high, wave-ready