Star0

Pre-install eval

Browser Agent eval report.

A machine-readable install decision for agents: task fit, Trust Score, Audit Score, install safety, permission surface, and a concrete validation plan before this skill touches a workspace.

Needs reviewMEDIUM RISKREVIEW POLICY
83
Eval
82
Trust
86
Audit
70
Safety

manual review

Review the audit page, then allow agent install in a sandboxed workflow.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate Browser Agent before installing it in an agent workflow
  • browser-automation
  • Testing and QA workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add magnitudedev/browser-agent

Install command safety

92

pass

standard package or runtime install path

  • npx skills add magnitudedev/browser-agent

Trust score

82

pass

Good trust signals with a few areas worth checking before rollout.

  • Strong shortlist
  • 4.1K GitHub stars
  • Apache-2.0

Audit score

86

pass

Safe to try

  • Documentation summary is thin

Agent safety gate

70

warn

Good audit and safety signals with no high-risk permission hints in public metadata.

  • Review the audit page, then allow agent install in a sandboxed workflow.
  • Safe-to-try audit

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

86

pass

network or browser access

  • Browser automation: medium
  • Network access: medium

Validation plan

What the agent should do next

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when

Conditions that require another skill

  • teams that need a vendor-supported SLA
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • Documentation summary is thin
  • README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
  • Production credentials, payments, or irreversible account changes without explicit human review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

fail

50

Public metadata needs stronger README/SKILL.md context

Recent maintenance

warn

76

5mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.