defender-secure-score-monitor Eval
==================================

Status: failed
Score: 62/100
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 ricmmartins/azure-sre-agent-skills --skill defender-secure-score-monitor

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
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The skill uses a placeholder <sub-id> for subscription ID; it could be improved by using environment variables or dynamic detection.
- The skill references execute_kusto_query but does not provide example Kusto queries or guidance on how to use it effectively.
- The SKILL.md excerpt is truncated at Step 6; the full document may contain more details, but the provided portion is sufficient for evaluation.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 70 GitHub stars
- Stars/forks activity: 70 stars, 14 forks; issue activity unavailable in current metadata

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 uses a placeholder <sub-id> for subscription ID; it could be improved by using environment variables or dynamic detection.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The skill references execute_kusto_query but does not provide example Kusto queries or guidance on how to use it effectively.
- The SKILL.md excerpt is truncated at Step 6; the full document may contain more details, but the provided portion is sufficient for evaluation.

URLs:
- Skill: https://www.openagentskill.com/skills/ricmmartins-defender-secure-score-monitor
- Audit: https://www.openagentskill.com/skills/ricmmartins-defender-secure-score-monitor/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=ricmmartins-defender-secure-score-monitor