agent-evaluation
Automates browser interactions for AI agents, enabling form filling, web scraping, and verification with deterministic actions.
Install this skill
or
96/100
Security score
The agent-evaluation skill was audited on May 19, 2026 and we found 4 security issues across 1 threat category. Review the findings below before installing.
Categories Tested
Security Issues
low line 33
External URL reference
SourceSKILL.md
| 33 | agent-browser open https://example.com/form |
low line 47
External URL reference
SourceSKILL.md
| 47 | agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i |
low line 113
External URL reference
SourceSKILL.md
| 113 | agent-browser --content-boundaries --max-output 50000 --allowed-domains "example.com,*.example.com" --action-policy ./policy.json open https://example.com |
low line 134
External URL reference
SourceSKILL.md
| 134 | - https://agent-browser.dev |
Scanned on May 19, 2026
View Security Dashboard