secret-handling Eval
====================

Status: failed
Score: 66/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Audit score: Risky

Install:
npx skills add microsoft/waza --skill secret-handling

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- WARN Install command safety: credential-bearing install command, standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- 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: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Install command safety: credential-bearing install command, standard package or runtime install path
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- Regex patterns may produce false positives (e.g., email addresses flagged as PII) which could block legitimate commits, but this is a minor trade-off for security.
- The skill focuses on .env and .squad files; it does not address secrets in other file types (e.g., .json configs, .yaml), which might be a gap in coverage.
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
- 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
- Regex patterns may produce false positives (e.g., email addresses flagged as PII) which could block legitimate commits, but this is a minor trade-off for security.
- No OpenAgentSkill engagement data yet
- Audit risk risky exceeds max_risk=medium
- 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/microsoft-secret-handling
- Audit: https://www.openagentskill.com/skills/microsoft-secret-handling/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=microsoft-secret-handling