Conversation
Closed
Agent-Logs-Url: https://github.com/camunda/BizSol_bb-ai-firewall-agent/sessions/f86fa402-ff3f-4394-b37a-f40a955a3444 Co-authored-by: vobu <6573426+vobu@users.noreply.github.com>
Agent-Logs-Url: https://github.com/camunda/BizSol_bb-ai-firewall-agent/sessions/f86fa402-ff3f-4394-b37a-f40a955a3444 Co-authored-by: vobu <6573426+vobu@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Copilot Request
Extend IT prompts with 59 attack pattern test cases across 10 categories
Apr 1, 2026
Test Coverage Report (Camunda 8.8)Docker image: Process Test Coverage (safeguard-agent): 100.0%✅ Meets minimum requirement (60%) 📊 Detailed reports available in build artifacts |
Test Coverage Report (Camunda 8.9)Docker image: Process Test Coverage (safeguard-agent): 100.0%✅ Meets minimum requirement (60%) 📊 Detailed reports available in build artifacts |
Test Coverage Report (Camunda 8.8)Docker image: Process Test Coverage (safeguard-agent): 100.0%✅ Meets minimum requirement (60%) 📊 Detailed reports available in build artifacts |
Test Coverage Report (Camunda 8.9)Docker image: Process Test Coverage (safeguard-agent): 100.0%✅ Meets minimum requirement (60%) 📊 Detailed reports available in build artifacts |
vobu
approved these changes
Apr 1, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds comprehensive prompt injection test coverage for 10 attack categories and hardens the system prompt to explicitly detect these patterns.
New prompt test files (59 total, all
blockcategory)override-*persona-*leaking-*nested-*delimiter-*encoding-*hypothetical-*escalation-*smuggling-*payload-*System prompt enhancements
Expanded the risk detection checklist and escalation rules in
safeguard-systemprompt.txt:developer mode,maintenance mode), prompt leaking (repeat everything above,translate your instructions), delimiter confusion (fake###SYSTEM###,[INST],<|im_start|>tokens), nested injection (directives embedded in documents/JSON/HTML/emails), payload splitting (code-word tricks, deferred instructions), incremental escalation (false precedents)All three prompt locations synced via
mvn compile exec:java(canonical txt → FEEL → BPMN embedding).