kimi-datasource Eval
====================

Status: failed
Score: 57/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Trust score: Potentially useful, but at least one trust signal needs human inspection.

Install:
npx skills add wangyuahn/nori-code --skill kimi-datasource

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
- FAIL 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:
- 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
- Financial research output is not financial advice; require human review before any live investment decision
- SKILL.md instructs agents to pass a file_path to many APIs, but does not explicitly restrict it to /tmp or warn against writing to sensitive locations. A malicious prompt or untrusted backend response could cause the agent to request file writes outside the intended output directory.
- The data returned from the backend may contain arbitrary content. SKILL.md does not warn agents to treat all returned data strictly as data, which could lead to indirect prompt injection if malformed metadata is misinterpreted as instructions.
- Low GitHub adoption signal
- Financial research output is not financial advice; require human review before any live investment decision.
- 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
- SKILL.md instructs agents to pass a file_path to many APIs, but does not explicitly restrict it to /tmp or warn against writing to sensitive locations. A malicious prompt or untrusted backend response could cause the agent to request file writes outside the intended output directory.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing

URLs:
- Skill: https://www.openagentskill.com/skills/wangyuahn-kimi-datasource
- Audit: https://www.openagentskill.com/skills/wangyuahn-kimi-datasource/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=wangyuahn-kimi-datasource