bids Eval
=========

Status: failed
Score: 77/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: shell or command execution, filesystem or document access

Install:
npx skills add K-Dense-AI/scientific-agent-skills --skill bids

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: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: https://creativecommons.org/licenses/by/4.0/
- FAIL Permission surface: shell or command execution, filesystem or document access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- 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
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The alternative Deno install command uses `-A` (allow all permissions), which grants excessive permissions to a globally installed script; this should be scoped or clearly explained if the agent is expected to run it.
- SKILL.md describes when to use the skill but lacks an explicit "When not to use" / limitations section, such as BIDS specification version drift, the need to manually verify DICOM conversion heuristics, and validation before dataset sharing.
- Permission surface needs review: shell or command execution, filesystem or document access
- Dependency/runtime risk: command execution surface, external package install surface
- Permission surface: shell or command execution, 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 alternative Deno install command uses `-A` (allow all permissions), which grants excessive permissions to a globally installed script; this should be scoped or clearly explained if the agent is expected to run it.
- High-risk permission hints: Shell or command execution
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- SKILL.md describes when to use the skill but lacks an explicit "When not to use" / limitations section, such as BIDS specification version drift, the need to manually verify DICOM conversion heuristics, and validation before dataset sharing.
- Permission surface needs review: shell or command execution, filesystem or document access

URLs:
- Skill: https://www.openagentskill.com/skills/k-dense-ai-bids
- Audit: https://www.openagentskill.com/skills/k-dense-ai-bids/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-bids