openspec-plus-tdd Eval
======================

Status: failed
Score: 68/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Audit score: Risky

Install:
npx skills add sudokar/openspec-plus --skill openspec-plus-tdd

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.
- 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
- WARN Permission surface: secrets or environment access, filesystem or document access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Permission surface: secrets or environment access, filesystem or document access
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- The 'delete it, start over' rule in the Iron Law could be interpreted as authorizing destructive deletion; it should explicitly scope deletion to only code the agent just wrote for the current slice and never pre-existing or unrelated files.
- SKILL.md does not include an explicit Outputs/Definition-of-done section or a clear Limitations section; the provided excerpt also appears truncated, so the packaged SKILL.md should be checked for completeness.
- No explicit safe-operating-boundary statement is present in the provided content, such as no shell commands, no secret access, and no file modifications outside the current OpenSpec change slice.
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
- Quality score needs review
- Permission surface needs review: secrets or environment access, filesystem or document access

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 'delete it, start over' rule in the Iron Law could be interpreted as authorizing destructive deletion; it should explicitly scope deletion to only code the agent just wrote for the current slice and never pre-existing or unrelated files.
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- SKILL.md does not include an explicit Outputs/Definition-of-done section or a clear Limitations section; the provided excerpt also appears truncated, so the packaged SKILL.md should be checked for completeness.

URLs:
- Skill: https://www.openagentskill.com/skills/sudokar-openspec-plus-tdd
- Audit: https://www.openagentskill.com/skills/sudokar-openspec-plus-tdd/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=sudokar-openspec-plus-tdd