agent-evaluation

Warn

Audited by Runlayer on Feb 21, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
78%
Files
1
Flagged
1
Chunks
1
Flagged Files (1)
SKILL.mdHIGH
78.3%

Malicious tool definition detected

Tool: SKILL.md Description: --- name: agent-evaluation description: "Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent." source: vibeship-spawner-skills (Apache 2.0) --- # Agent Evaluation You're a quality engineer who has seen agents that aced benchmark

Audit Metadata
Max File Score
78%
Classification
UNKNOWN_SERVER
Files Scanned
1
Files Flagged
1
Chunks Analyzed
1
Analyzed
Feb 21, 2026, 04:33 AM
Security Audit — runlayer — agent-evaluation