OpenAgentSkill
GitHub200+

Pre-install eval

lead-research 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
68
Eval report
66
Trust
73
Audit
57
Agent safety

manual review

Test manually in an isolated workspace and compare against safer alternatives.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

94

pass

Task wording matches this skill metadata.

  • Evaluate lead-research before installing it in an agent workflow
  • research
  • Sales and CRM workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add sandbaseai/sandbase-skills --skill lead-research

Install command safety

92

pass

standard package or runtime install path

  • npx skills add sandbaseai/sandbase-skills --skill lead-research

Trust score

66

warn

Potentially useful, but at least one trust signal needs human inspection.

  • Manual review
  • 68 GitHub stars
  • Apache-2.0

Audit score

73

warn

Needs review

  • The SKILL.md does not instruct the agent to treat external tool output as untrusted data; malicious content returned from LinkedIn or other sources could attempt prompt injection.

Agent safety gate

57

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The SKILL.md does not instruct the agent to treat external tool output as untrusted data; malicious content returned from LinkedIn or other sources could attempt prompt injection.

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

74

warn

network or browser access, database access

  • Network access: medium
  • Database 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
  • production agents without a repository review
  • The SKILL.md does not instruct the agent to treat external tool output as untrusted data; malicious content returned from LinkedIn or other sources could attempt prompt injection.
  • No OpenAgentSkill engagement data yet
  • The API map is essentially a placeholder: every entry says 'See sandbase_describe_tool for details,' so the skill does not document what each tool actually does or returns.
  • No explicit privacy or data-minimization guidance is provided for handling personal information of leads, despite the skill being centered on collecting prospect intelligence.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

76

Public metadata needs stronger README/SKILL.md context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.