Evals
Provides a comprehensive framework for evaluating AI agents using various grading methods and metrics to ensure quality and performance.
Install this skill
or
81/100
Security score
The Evals skill was audited on Mar 1, 2026 and we found 11 security issues across 3 threat categories. Review the findings below before installing.
Categories Tested
Security Issues
medium line 22
Curl to non-GitHub URL
SourceSKILL.md
| 22 | curl -s -X POST http://localhost:8888/notify \ |
medium line 11
Access to hidden dotfiles in home directory
SourceSKILL.md
| 11 | `~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Evals/` |
low line 96
Access to hidden dotfiles in home directory
SourceSKILL.md
| 96 | bun run ~/.claude/skills/Evals/Tools/AlgorithmBridge.ts -s <suite> |
low line 99
Access to hidden dotfiles in home directory
SourceSKILL.md
| 99 | bun run ~/.claude/skills/Evals/Tools/FailureToTask.ts log "description" -c category -s severity |
low line 102
Access to hidden dotfiles in home directory
SourceSKILL.md
| 102 | bun run ~/.claude/skills/Evals/Tools/FailureToTask.ts convert-all |
low line 105
Access to hidden dotfiles in home directory
SourceSKILL.md
| 105 | bun run ~/.claude/skills/Evals/Tools/SuiteManager.ts create <name> -t capability -d "description" |
low line 106
Access to hidden dotfiles in home directory
SourceSKILL.md
| 106 | bun run ~/.claude/skills/Evals/Tools/SuiteManager.ts list |
low line 107
Access to hidden dotfiles in home directory
SourceSKILL.md
| 107 | bun run ~/.claude/skills/Evals/Tools/SuiteManager.ts check-saturation <name> |
low line 108
Access to hidden dotfiles in home directory
SourceSKILL.md
| 108 | bun run ~/.claude/skills/Evals/Tools/SuiteManager.ts graduate <name> |
low line 117
Access to hidden dotfiles in home directory
SourceSKILL.md
| 117 | bun run ~/.claude/skills/Evals/Tools/AlgorithmBridge.ts -s regression-core -r 3 -u |
low line 22
External URL reference
SourceSKILL.md
| 22 | curl -s -X POST http://localhost:8888/notify \ |
Scanned on Mar 1, 2026
View Security DashboardGitHub Stars 9.6K
Rate this skill
Categorydevelopment
UpdatedApril 10, 2026
claude-codeapiml-ai-engineerqa-engineerdata-scientistproduct-managertechnical-pmdevelopmentdata analyticsproduct
danielmiessler/Personal_AI_Infrastructure