biopython Eval
==============

Status: failed
Score: 72/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: secrets or environment access, shell or command execution

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

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: Biopython License Agreement
- FAIL Permission surface: secrets or environment access, 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.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- SKILL.md references `references/sequence_io.md` for sequence handling, but the submitted skill directory only includes `advanced.md`, `alignment.md`, `blast.md`, `databases.md`, and `phylogenetics.md`. The referenced file appears to be missing.
- The NCBI_EMAIL environment variable is listed as optional in metadata, while the documentation correctly states that NCBI policy requires an email for Entrez. The example hardcodes a placeholder instead of reading from the environment, which may cause failed Entrez calls.
- The skill does not include an explicit license/attribution notice beyond the repository license declaration. If the content is derived from Biopython documentation, upstream copyright and license notices should be preserved.
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution

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
- SKILL.md references `references/sequence_io.md` for sequence handling, but the submitted skill directory only includes `advanced.md`, `alignment.md`, `blast.md`, `databases.md`, and `phylogenetics.md`. The referenced file appears to be missing.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The NCBI_EMAIL environment variable is listed as optional in metadata, while the documentation correctly states that NCBI policy requires an email for Entrez. The example hardcodes a placeholder instead of reading from the environment, which may cause failed Entrez calls.
- The skill does not include an explicit license/attribution notice beyond the repository license declaration. If the content is derived from Biopython documentation, upstream copyright and license notices should be preserved.

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