tax-dispute-response Eval
=========================

Status: review
Score: 62/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add guoliang1114-boop/AriaAI --skill tax-dispute-response

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
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- WARN Permission surface: shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Permission surface: shell or command execution
- High-risk permission hints: Shell or command execution
- No explicit setup/requirements section and no dedicated limitations/disclaimer; users may not know operational prerequisites or that the output should be validated by a tax professional.
- Some legal references appear outdated or superseded (e.g., 国税发〔2009〕157号 and 国税发〔2009〕2号 may have been replaced by newer rules; 《行政处罚法》 article numbers reflect the old law).
- No explicit prompt-injection guardrail for external content; the skill uses read/webfetch on tax notices, contracts, and web pages without stating that such content must be treated as untrusted data.
- The repository timestamp appears to be in the future relative to the review date; metadata consistency should be verified.
- Low GitHub adoption signal
- 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
- Low GitHub adoption signal
- No explicit setup/requirements section and no dedicated limitations/disclaimer; users may not know operational prerequisites or that the output should be validated by a tax professional.
- High-risk permission hints: Shell or command execution
- Some legal references appear outdated or superseded (e.g., 国税发〔2009〕157号 and 国税发〔2009〕2号 may have been replaced by newer rules; 《行政处罚法》 article numbers reflect the old law).
- No explicit prompt-injection guardrail for external content; the skill uses read/webfetch on tax notices, contracts, and web pages without stating that such content must be treated as untrusted data.
- The repository timestamp appears to be in the future relative to the review date; metadata consistency should be verified.

URLs:
- Skill: https://www.openagentskill.com/skills/guoliang1114-boop-tax-dispute-response
- Audit: https://www.openagentskill.com/skills/guoliang1114-boop-tax-dispute-response/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=guoliang1114-boop-tax-dispute-response