https://clawhub.ai/api/v1/skills/chengjun-content-security/file?path=SKILL.md&version=1.0.2
github.com/clawhub.ai/chengjun-content-security
Scanned Thu, 28 May 2026 16:25:21 GMT
Scan ID crawl-iq7d1xvtk60yjbpdr9karrcd · 2ms
A
SCORE 95 / 100
Verdict: Safe to install

2 medium findings.

This skill ships without a capability manifest plus 1 other issue listed below.

0 critical0 high2 medium10 rules passed

Why grade A?

score · 95 / 100

The current grade reflects 2 minor findings below all thresholds.

0 CRIT0 HIGH2 MED0 LOW

Already at the top grade — no further rules to pass.

Findings · ordered by severity

med
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule: no-manifest
med
Skill name mixes ASCII with lookalike non-ASCII characters
The skill name `成均内容安全 description: 通过调用成均平台的HTTP API接口,检测文本中的敏感信息、语法错误、标点符号问题等,保障内容合规。` contains characters that visually resemble ASCII letters but are from a different script: , (U+FF0C), , (U+FF0C). This is the standard typosquat pattern — installers think they're getting `stripe/checkout` and end up with a malicious lookalike.
rule: unicode-homoglyphline: 3CWE-1007
name: 成均内容安全 description: 通过调用成均平台的HTTP API接口,检测文本中的敏感信息、语法错误、标点符号问题等,保障内容合规。
Scan another →Share
skillox.io/r/crawl-iq7d1xvtk60yjbpdr9karrcd