exit-strategy Eval
==================

Status: review
Score: 65/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add kucherenko/gangsta --skill exit-strategy

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
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- WARN Permission surface: shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Permission surface: shell or command execution
- High-risk permission hints: Shell or command execution
- Financial research output is not financial advice; require human review before any live investment decision
- Test command in Step 1 is a generic placeholder (npm test / cargo test / pytest / go test ./...), which may not match the actual project and could lead the agent to run the wrong command.
- SKILL.md does not define an explicit inputs section for branch name, base branch, test command, or safehouse path, leaving some ambiguity for agent execution.
- Option 4 destructive cleanup relies on typed confirmation but does not explicitly instruct the agent to validate that the branch name is not a protected branch like main or master before deletion.
- Financial research output is not financial advice; require human review before any live investment decision.
- 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
- Test command in Step 1 is a generic placeholder (npm test / cargo test / pytest / go test ./...), which may not match the actual project and could lead the agent to run the wrong command.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- Financial research output is not financial advice; require human review before any live investment decision
- SKILL.md does not define an explicit inputs section for branch name, base branch, test command, or safehouse path, leaving some ambiguity for agent execution.
- Option 4 destructive cleanup relies on typed confirmation but does not explicitly instruct the agent to validate that the branch name is not a protected branch like main or master before deletion.

URLs:
- Skill: https://www.openagentskill.com/skills/kucherenko-exit-strategy
- Audit: https://www.openagentskill.com/skills/kucherenko-exit-strategy/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=kucherenko-exit-strategy