OpenAgentSkill
GitHub200+

Pre-install eval

hunt-clickjacking 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
71
Eval report
73
Trust
80
Audit
52
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

70

warn

Task fit is weak; compare alternatives before selecting.

  • Evaluate hunt-clickjacking before installing it in an agent workflow
  • design-creative
  • Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add elementalsouls/Claude-BugHunter --skill hunt-clickjacking

Install command safety

92

pass

standard package or runtime install path

  • npx skills add elementalsouls/Claude-BugHunter --skill hunt-clickjacking

Trust score

73

warn

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

  • Strong shortlist
  • 4.1K GitHub stars
  • MIT

Audit score

80

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

52

warn

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • High-risk permission hints: Secrets or environment access

License clarity

86

pass

MIT

  • MIT

Permission surface

60

warn

secrets or environment access, network or browser access

  • Browser automation: medium
  • Network access: medium
  • Secrets or environment access: high

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 does not explicitly state that testing must be limited to authorized targets, bug bounty scopes, or environments the user owns/has permission to test.
  • High-risk permission hints: Secrets or environment access
  • Permission surface may require sandboxing
  • The example curl command only checks the top-level response headers; for authenticated or client-side rendered pages, header inspection may need to be repeated after login or on the actual action endpoint.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.