Star200+

Pre-install eval

guidelines-advisor 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
78
Eval report
76
Trust
84
Audit
64
Agent safety

manual review

Require human approval before installing into a real workspace.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate guidelines-advisor before installing it in an agent workflow
  • research
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add trailofbits/skills --skill guidelines-advisor

Install command safety

92

pass

standard package or runtime install path

  • npx skills add trailofbits/skills --skill guidelines-advisor

Trust score

76

warn

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

  • Strong shortlist
  • 6.8K GitHub stars
  • CC-BY-SA-4.0

Audit score

84

warn

Needs review

  • The skill's security posture is sound as it only analyzes code and generates recommendations; no destructive or high-risk operations are performed.

Agent safety gate

64

warn

Usable candidate, but the agent should surface permission and audit notes before installation.

  • Require human approval before installing into a real workspace.
  • The skill's security posture is sound as it only analyzes code and generates recommendations; no destructive or high-risk operations are performed.

License clarity

86

pass

CC-BY-SA-4.0

  • CC-BY-SA-4.0

Permission surface

74

warn

filesystem or document access, database access

  • Network access: medium
  • Filesystem 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's security posture is sound as it only analyzes code and generates recommendations; no destructive or high-risk operations are performed.
  • No OpenAgentSkill engagement data yet
  • Minor concern: the skill references external resources (ASSESSMENT_AREAS.md, EXAMPLE_REPORT.md) that are included, but their completeness is not fully verified in this review.
  • The skill does not explicitly state limitations or safe operating boundaries in SKILL.md, which could be improved.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

Pushed today

Alternatives available

pass

82

Alternative skills are available for comparison.