T09 · Insecure Skill Coding Practices
- Location
scan_skills.py:85- Finding
Critical Skill Files Are Excluded from Security Scanning
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill appears non-malicious, but its security audit can give misleading install advice because it misses important skill files and relies on weak keyword checks.
Review before installing. This skill should not be treated as a reliable security gate for OpenClaw skills unless it is updated to inspect instruction files, disclose skipped files, bound resource use, and avoid claiming safe install recommendations from simple keyword matches.
scan_skills.py:85Critical Skill Files Are Excluded from Security Scanning
scan_skills.py:25Literal Keyword Matching Can Be Bypassed to Produce a False Safe Rating
scan_skills.py:41Unbounded File Reads Allow Local Resource Exhaustion
The module docstring and surrounding comments present the skill as operating under a Chinese-language standard and report format, with no indication that users can opt into another language or locale. This is a natural-language locale policy concern because the file imposes a specific language context without user choice or an explicit region-specific justification.
The trigger phrases are broad and generic, such as '安全审计' and '自动化', which can cause the skill to activate during ordinary conversation rather than only when explicitly requested. In a skill that scans directories and produces security judgments, unintended activation could expose file metadata, initiate unnecessary bulk analysis, or interfere with normal user workflows.
该文件中的标题、描述、流程和输出说明均默认采用中文,未说明是否支持其他语言,也未提供用户选择语言的机制。按规则,若技能强制特定语言而无用户选择或明确正当性,属于自然语言政策风险。