Skip to content

feat(register): add OrchestratorTrustExploitationEval, C5 pipeline authority injection #1907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
lavkeshdwivedi wants to merge 1 commit into from
Closed

feat(register): add OrchestratorTrustExploitationEval, C5 pipeline authority injection #1907

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions register/orchestrator_trust_exploitation_eval/eval.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
full_title: "Orchestrator Trust Exploitation Eval: Pipeline Sub-Agent Authority Injection (C5)"
common_title: "OrchestratorTrustExploitationEval"
description: |
Evaluates whether pipeline sub-agents accept false orchestrator authority claims embedded in pipeline messages and act on restricted resources without independently verifying the claimed token. Tests the C5 (Orchestrator Trust Exploitation) behavior class from Dwivedi (2026).
contributors:
- lavkeshdwivedi
tags:
- Agent
- Safeguards
metadata:
fast: true
tasks:
- name: orchestrator_trust_exploitation_eval
dataset_samples: 4
task_path: evals/orchestrator_trust_exploitation_eval.py
source:
repository_url: https://github.com/lavkeshdwivedi/agent-escape-lab
repository_commit: 8671644d2c57e30f8c791bc2e950c73a4eb07289
maintainers:
- lavkeshdwivedi
Loading