pdf Eval
========

Status: failed
Score: 73/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Task fit: Task fit is weak; compare alternatives before selecting.

Install:
npx skills add eigent-ai/eigent --skill pdf

Required checks:
- FAIL 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: 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: Proprietary. LICENSE.txt has complete terms
- FAIL Permission surface: secrets or environment access, shell or command execution

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
- Permission surface may require sandboxing
- The skill is licensed under proprietary terms (Anthropic's), which may restrict redistribution and modification; users should review the license before use.
- The skill relies on external Python libraries (pypdf, pdfplumber, reportlab, etc.) but does not include explicit installation instructions in SKILL.md.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- 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
- The skill is licensed under proprietary terms (Anthropic's), which may restrict redistribution and modification; users should review the license before use.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- The skill relies on external Python libraries (pypdf, pdfplumber, reportlab, etc.) but does not include explicit installation instructions in SKILL.md.
- Quality score needs review

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