foundation-models Eval
======================

Status: failed
Score: 68/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: shell or command execution, network or browser access

Install:
npx skills add rshankras/claude-code-apple-skills --skill foundation-models

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
- FAIL Permission surface: shell or command execution, network or browser access

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.
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- No explicit prompt-injection defense guidance appears in SKILL.md; companion safety docs cover guardrails, but a dedicated note about untrusted input handling would strengthen the skill.
- Bash is listed as an allowed tool even though the documented workflow is primarily code reference and editing; unnecessary shell access broadens the agent's permission surface.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: shell or command execution, network or browser access
- Permission surface: shell or command execution, network or browser 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
- No explicit prompt-injection defense guidance appears in SKILL.md; companion safety docs cover guardrails, but a dedicated note about untrusted input handling would strengthen the skill.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Bash is listed as an allowed tool even though the documented workflow is primarily code reference and editing; unnecessary shell access broadens the agent's permission surface.

URLs:
- Skill: https://www.openagentskill.com/skills/rshankras-foundation-models
- Audit: https://www.openagentskill.com/skills/rshankras-foundation-models/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=rshankras-foundation-models