Loading ToolBench
Reading the current corpus…
Skip to content
toolbench
Browse
Insights
Methodology
☾
skill-audit MCP server · F · ToolBench
← Browse
skill-audit
github.com/ondrej-merkun/skill-audit
Scan AI agent skills for prompt injection and malicious code
2026-07-28+
STDIO
0 tools
F
15
/100
Definition Quality
0
Protocol Readiness
0
Supportability
25
Spec posture
Inferred effective spec
2026-07-28+
·
current baseline
2026-07-28
Static source inference · medium confidence
Current-spec patterns detected
Summary
Scoring was not performed
Score history
Overall score trend
First recorded score · v2 rubric
15
/100
100
50
0
2026-09-23: 15/100 (F) · v2 rubric
15 · F
2026-09-23 · v2
Scored
Grade
Overall
Spec posture
Rubric
2026-09-23
F
15
2026-07-28+
v2