html-ppt-zhangzara-cartesian Eval
=================================

Status: failed
Score: 84/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Audit score: Risky

Install:
npx skills add nexu-io/open-design --skill html-ppt-zhangzara-cartesian

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.
- FAIL Audit score: Risky
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: Apache-2.0
- PASS Permission surface: filesystem or document access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit risk risky exceeds max_risk=medium
- Financial research output is not financial advice; require human review before any live investment decision
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- The provided file listing shows only SKILL.md and template.json, while SKILL.md instructs agents to clone example.html and states that the full MIT LICENSE ships in the skill. If those files are not actually present in the submitted skill package, the workflow is not executable and the license redistribution requirement is not satisfied.
- The template.json excerpt appears truncated at the navigation field, so the complete upstream metadata snapshot could not be fully verified.
- The vendored example.html or asset runtime is not included in the review excerpt, so the inline keyboard handler/JS could not be audited for hidden behavior.
- Financial research output is not financial advice; require human review before any live investment decision.
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.

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 provided file listing shows only SKILL.md and template.json, while SKILL.md instructs agents to clone example.html and states that the full MIT LICENSE ships in the skill. If those files are not actually present in the submitted skill package, the workflow is not executable and the license redistribution requirement is not satisfied.
- Audit risk risky exceeds max_risk=medium
- Financial research output is not financial advice; require human review before any live investment decision
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- The template.json excerpt appears truncated at the navigation field, so the complete upstream metadata snapshot could not be fully verified.
- The vendored example.html or asset runtime is not included in the review excerpt, so the inline keyboard handler/JS could not be audited for hidden behavior.

URLs:
- Skill: https://www.openagentskill.com/skills/nexu-io-html-ppt-zhangzara-cartesian
- Audit: https://www.openagentskill.com/skills/nexu-io-html-ppt-zhangzara-cartesian/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=nexu-io-html-ppt-zhangzara-cartesian