Star0

Pre-install eval

Scavenger 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
60
Eval
70
Trust
64
Audit
36
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

84

pass

Task wording matches this skill metadata.

  • Evaluate Scavenger before installing it in an agent workflow
  • web-automation
  • Web scraping workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add rndinfosecguy/Scavenger

Install command safety

92

pass

standard package or runtime install path

  • npx skills add rndinfosecguy/Scavenger

Trust score

70

warn

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

  • Manual review
  • 810 GitHub stars
  • MIT

Audit score

64

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

36

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, filesystem or document access

  • Network access: medium
  • Filesystem 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 require actively maintained dependencies
  • production agents without a repository review
  • Repository looks stale
  • High-risk permission hints: Secrets or environment access
  • Permission surface may require sandboxing
  • Repository appears stale

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

74

Public metadata needs stronger README/SKILL.md context

Recent maintenance

fail

22

4y since push

Alternatives available

pass

82

Alternative skills are available for comparison.