ClawHub
Back to skill

Security audit

skill-auditor

Security checks across malware telemetry and agentic risk

Overview

This skill is a local SKILL.md quality auditor with a helper script, and its file access is limited and consistent with that purpose.

Install this if you are comfortable with a Chinese-first skill that runs a local Python script over a SKILL.md and nearby skill directory structure. Review its findings as quality guidance, not as a security guarantee or automatic fixer.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
模块说明将能力描述为针对 SKILL.md 内容的检测，但实现中不仅读取目标文件，还依据同级目录下的 scripts/、references/、templates/ 是否存在以及其中是否有文件来决定类型和多个维度分数（如 L25-L26、L90-L96、L120-L126、L141-L147、L165-L170）。这使实际行为超出了“检测 SKILL.md 关键模式”的表述范围，属于描述与行为不一致。

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
This markdown file is entirely written in Chinese and does not state within the file that language selection is optional or user-driven. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue, even though an English counterpart is linked.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation list includes generic phrases such as “审阅skill”, “检查skill质量”, and “优化skill”, which could match many ordinary conversations about skills rather than a clearly scoped invocation. The file does not provide exclusion conditions or negative examples to distinguish when this skill should or should not activate.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The manifest description is entirely in Chinese and the document consistently instructs behavior in that language, but there is no indication that language selection is user-configurable or limited to a region-specific use case. Per the policy, forcing a specific language without opt-in can be a natural-language policy issue.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The module docstring states the script's purpose, usage, and output entirely in Chinese, and the generated report and CLI help are also hard-coded in Chinese later in the file. This imposes a specific language/locale on users without any visible opt-in or alternative, which matches the language-policy violation criteria.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
The report formatter and argparse descriptions emit user-facing text such as report headings, labels, improvement notices, and help text only in Chinese. Because the script does not provide a locale choice or documented justification for this restriction, it violates the natural-language policy requirement.

Scope Creep

Low
Category
Excessive Agency
Content
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.