ko-tech-writer Eval
===================

Status: failed
Score: 62/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: shell or command execution, filesystem or document access

Install:
npx skills add chrono-meta/forge-harness --skill ko-tech-writer

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
- Permission surface may require sandboxing
- The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.
- The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.
- The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 14 GitHub stars

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
- Low GitHub adoption signal
- The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.
- The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.

URLs:
- Skill: https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer
- Audit: https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=chrono-meta-ko-tech-writer