# Malicious Skill Detection on MaliciousAgentSkillsBench (404 malicious, 502 benign) Source: [Malicious Skill Detection on MaliciousAgentSkillsBench (404 malicious, 502 benign)]() Collection index: [llms.txt]() Data updated: 2026-05-13T09:35:09.036Z Evaluation of model performance for detecting malicious skills using the MaliciousAgentSkillsBench dataset, which contains 404 malicious samples and 502 benign samples. Performance is typically measured using 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 skill detection | | Dataset (including any stated split) | MaliciousAgentSkillsBench (404 malicious, 502 benign) | | Metric | Recall | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Recall](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Recall | Result date | Report paper | | --- | --- | --- | --- | | BIV | 100 | Not recorded | 6a040597dbc836b87d82753c | | BIV | 98 | Not recorded | 6a040597dbc836b87d82753c | | LLM-only | 93 | Not recorded | 6a040597dbc836b87d82753c | | LLM-only | 89 | Not recorded | 6a040597dbc836b87d82753c | | BIV | 86 | Not recorded | 6a040597dbc836b87d82753c | | LLM-only | 64 | Not recorded | 6a040597dbc836b87d82753c | | Rule-based | 45 | Not recorded | 6a040597dbc836b87d82753c | | Rule-based | 39 | Not recorded | 6a040597dbc836b87d82753c | | Rule-based | 35 | Not recorded | 6a040597dbc836b87d82753c | ### BIV Recall: 100. Result ID: 6a0445ba47f34ce924ea7c53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### BIV Recall: 98. Result ID: 6a0445ba47f34ce924ea7c56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### LLM-only Recall: 93. Result ID: 6a0445ba47f34ce924ea7c52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLM-only Recall: 89. Result ID: 6a0445ba47f34ce924ea7c55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BIV Recall: 86. Result ID: 6a0445ba47f34ce924ea7c4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### LLM-only Recall: 64. Result ID: 6a0445ba47f34ce924ea7c4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rule-based Recall: 45. Result ID: 6a0445ba47f34ce924ea7c51. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rule-based Recall: 39. Result ID: 6a0445ba47f34ce924ea7c4b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rule-based Recall: 35. Result ID: 6a0445ba47f34ce924ea7c54. [Reporting paper]() 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.