evaluation-task · Source-linked discovery

CodeIPI: Indirect Prompt Injection for Coding Agents

Measures coding agent vulnerability to indirect prompt injection attacks embedded in software engineering artifacts (issue descriptions, code comments, README files). Each sample pairs a legitimate bug-fixing task with an injected payload. Scoring measures injection resistance, task completion, and detection.

Open interactive record →
OriginDebu SinhaTopicsAutonomy & agents · CyberStatusimported

Can support

Not independently assessed by FronteraEval yet.

Cannot support by itself

No inference beyond the upstream source should be made until the protocol is reviewed.

Original sources