frontend-specialist Eval
========================

Status: failed
Score: 59/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Agent safety gate: This skill should not be selected by an agent without explicit human security review.

Install:
npx skills add huangwb8/skills --skill frontend-specialist

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: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Platform-specific references to `.bensz-api` task workspaces and `bensz-collect-bugs`/`~/.bensz-skills/bugs/` are undocumented external conventions; agents outside that ecosystem may be confused or may create unexpected hidden directories.
- No explicit safety guardrails for browser/Playwright operations, such as limiting execution to the project workspace, avoiding destructive commands, or protecting secrets; the skill relies on the host agent's general safety.
- SKILL.md lacks a dedicated 'Setup' or 'Limitations' section describing required dependencies, such as Playwright browsers, and cases where the skill should stop or ask for clarification.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution

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
- Low GitHub adoption signal
- Platform-specific references to `.bensz-api` task workspaces and `bensz-collect-bugs`/`~/.bensz-skills/bugs/` are undocumented external conventions; agents outside that ecosystem may be confused or may create unexpected hidden directories.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- No explicit safety guardrails for browser/Playwright operations, such as limiting execution to the project workspace, avoiding destructive commands, or protecting secrets; the skill relies on the host agent's general safety.

URLs:
- Skill: https://www.openagentskill.com/skills/huangwb8-frontend-specialist
- Audit: https://www.openagentskill.com/skills/huangwb8-frontend-specialist/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=huangwb8-frontend-specialist