docx Eval
=========

Status: review
Score: 70/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add axoviq-ai/synthadoc --skill docx

Required checks:
- WARN Task fit: Task fit is weak; compare alternatives before selecting.
- 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: AGPL-3.0-or-later
- WARN Permission surface: shell or command execution, filesystem or document access

Warnings:
- Task fit: Task fit is weak; compare alternatives before selecting.
- 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, filesystem or document access
- High-risk permission hints: Shell or command execution
- SKILL.md does not mention that extracted Word document content should be treated as untrusted data, which is relevant for agents that might interpret document text as instructions.
- SKILL.md documents paragraph extraction but does not note that tables, headers, footers, and text boxes are ignored.
- No guidance on handling unusually large or malformed .docx files; python-docx parsing can consume significant memory if given a crafted or zip-bomb-like document.
- 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
- SKILL.md does not mention that extracted Word document content should be treated as untrusted data, which is relevant for agents that might interpret document text as instructions.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- SKILL.md documents paragraph extraction but does not note that tables, headers, footers, and text boxes are ignored.
- No guidance on handling unusually large or malformed .docx files; python-docx parsing can consume significant memory if given a crafted or zip-bomb-like document.
- Quality score needs review

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