image-utils Eval
================

Status: failed
Score: 65/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: shell or command execution, filesystem or document access

Install:
npx skills add Bria-AI/bria-skill --skill image-utils

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, filesystem or document 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
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Image loading from URLs does not appear to enforce a maximum file size or decompression-bomb limit, which can be risky when processing untrusted images.
- URL loading also does not restrict schemes or network targets; if exposed to untrusted user input, this could enable SSRF-style access to internal resources.
- SKILL.md does not explain how the image_utils.py module becomes importable, since the code lives under references/code-examples; agents may not know how to install or reference it.
- There is no explicit limitations section covering EXIF orientation, ICC color profiles, alpha handling, or recompression artifacts from lossy format conversion.
- Quality score needs review
- Permission surface needs review: 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
- Image loading from URLs does not appear to enforce a maximum file size or decompression-bomb limit, which can be risky when processing untrusted images.
- High-risk permission hints: Shell or command execution
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- URL loading also does not restrict schemes or network targets; if exposed to untrusted user input, this could enable SSRF-style access to internal resources.
- SKILL.md does not explain how the image_utils.py module becomes importable, since the code lives under references/code-examples; agents may not know how to install or reference it.

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