# Malicious Instruction Detection on MaliciousAgentSkillsBench (traditional IPI baselines)

Source: [Malicious Instruction Detection on MaliciousAgentSkillsBench (traditional IPI baselines)](<https://www.sota2.com/research/sota/malicious-instruction-detection-on-maliciousagentskillsbench-traditional-ipi-baselines>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-28T07:10:13.793Z

Evaluation of model performance for detecting malicious instructions using the MaliciousAgentSkillsBench dataset under traditional IPI baseline settings, measured by Precision, Recall, and F1 Score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Malicious Instruction Detection |
| Dataset (including any stated split) | MaliciousAgentSkillsBench traditional IPI baselines |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Precision](<https://www.sota2.com/research/sota/malicious-instruction-detection-on-maliciousagentskillsbench-traditional-ipi-baselines.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/malicious-instruction-detection-on-maliciousagentskillsbench-traditional-ipi-baselines.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/malicious-instruction-detection-on-maliciousagentskillsbench-traditional-ipi-baselines.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| RouteGuard | 63.93 | Not recorded | 69f03f0e55a3c32af89fa002 |
| RENNERVATE | 47.76 | Not recorded | 69f03f0e55a3c32af89fa002 |
| ASen | 36.76 | Not recorded | 69f03f0e55a3c32af89fa002 |
| PArm | 24 | Not recorded | 69f03f0e55a3c32af89fa002 |

### RouteGuard

Precision: 63.93. Result ID: 69f05d4b47f34ce924d5bea7.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f0e55a3c32af89fa002.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f0e55a3c32af89fa002.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RENNERVATE

Precision: 47.76. Result ID: 69f05d4b47f34ce924d5bea6.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f0e55a3c32af89fa002.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6938fe806cfd488761a53c13.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ASen

Precision: 36.76. Result ID: 69f05d4b47f34ce924d5bea5.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f0e55a3c32af89fa002.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PArm

Precision: 24. Result ID: 69f05d4b47f34ce924d5bea4.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f0e55a3c32af89fa002.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a161e209131cea810e7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.