az-eu-website-privacy-audit Eval
================================

Status: review
Score: 74/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add lawve-ai/awesome-legal-skills --skill az-eu-website-privacy-audit

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: CC BY 4.0
- WARN Permission surface: filesystem or document access, network or browser access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- Permission surface: filesystem or document access, network or browser access
- The skill processes user-provided URLs and pasted website content, but SKILL.md does not explicitly instruct the model to treat website content as untrusted data and ignore any instructions embedded in it, which is a prompt-injection consideration.
- The report template and references are detailed, but SKILL.md does not include a fallback procedure if the submitted URL is unreachable, requires authentication, or contains dynamic content that cannot be fully audited.
- Quality score needs review

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

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- The skill processes user-provided URLs and pasted website content, but SKILL.md does not explicitly instruct the model to treat website content as untrusted data and ignore any instructions embedded in it, which is a prompt-injection consideration.
- No OpenAgentSkill engagement data yet
- The report template and references are detailed, but SKILL.md does not include a fallback procedure if the submitted URL is unreachable, requires authentication, or contains dynamic content that cannot be fully audited.
- Quality score needs review
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface

URLs:
- Skill: https://www.openagentskill.com/skills/lawve-ai-az-eu-website-privacy-audit
- Audit: https://www.openagentskill.com/skills/lawve-ai-az-eu-website-privacy-audit/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=lawve-ai-az-eu-website-privacy-audit