T09 · Insecure Skill Coding Practices
- Location
scripts/fact-check.js:28- Finding
Shell Command Injection Through Fact-Check Input
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This fact-checking skill is mostly purpose-aligned, but its script can turn text being checked into shell command execution.
Review before installing. The skill’s goal is coherent, but it should replace execSync string interpolation with execFileSync or another argument-array API, add input length and timeout controls, and warn users not to submit secrets or confidential text to online search.
scripts/fact-check.js:28Shell Command Injection Through Fact-Check Input
SKILL.md:98Unpinned Package Execution in Installation Instructions
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
---
name: ai-fact-checker
description: 🔍 AI 事实核查 - 自动验证大模型输出准确性,检测 hallucination 幻觉编造内容,联网搜索交叉验证给出可信度评分和修正。解决大模型一本正经胡说八道的痛点。
---
# 🔍 AI Fact Checker - AI 事实核查
自动验证 AI 输出信息的真实性,检测幻觉(hallucination)编造内容,联网搜索交叉验证,给出可信度评分,并自动修正错误信息。
## ✨ 痛点解决
大模型经常一本正经地**胡说八道**:编造不存在的论文、数据、人名、事件、网址。这个技能帮你:
The skill explicitly says it performs online cross-verification via search, but the user-facing description does not clearly warn that submitted content will be sent to external search services. Users may paste sensitive, proprietary, or regulated data into the fact-checker without realizing it will leave the local environment.
The installation command uses npx clawhub without pinning a specific version, so users may execute whatever package version is current at install time. That creates a supply-chain risk: a compromised or maliciously updated package could run arbitrary code on the user's machine during install or execution.
The skill builds a shell command with user-derived content and executes it via execSync, which invokes a shell. Although double quotes are escaped, shell metacharacters such as backticks or command substitution syntax are not neutralized, so crafted input can break the intended boundary and trigger arbitrary local command execution. In a fact-checking skill, this is especially dangerous because it processes untrusted free-form text by design.
The skill sends user-provided text to an external search service without explicit notice or consent. Because the input can contain sensitive or proprietary content, this creates a privacy and data-exfiltration risk, and a fact-checking workflow makes such transmission likely and repeated for multiple extracted statements.
The report verdicts, reasons, and summary strings are all emitted in Chinese, forcing a specific language regardless of user preference. This is a natural-language policy concern unless the locale restriction is explicitly documented and justified, which is not present in this file.
The skill's description and operating instructions are presented entirely in Chinese, while the file does not indicate that the skill is region-specific or that users may choose another language. This can violate a language/locale policy when a skill implicitly forces one language without opt-in.
This text is written entirely in Chinese and does not indicate that the skill is region-specific or that users can choose another language. Under the language/locale policy rule, forcing a specific language without opt-in can be a policy concern.
The package description is written entirely in Chinese, which indicates a language-specific presentation without any visible opt-in or alternative language option. Under the policy, forcing a specific language without user choice can be a natural-language locale violation unless the regional constraint is explicitly documented and justified.
The comment frames this as use of a web search tool, which implies a direct tool integration, but the code actually constructs a shell command and executes it with execSync. That documentation omits and thereby misrepresents the significant behavior of invoking a subprocess on the host.
This JavaScript test file includes user-facing natural-language content in Chinese, and subsequent console output also uses Chinese phrases for statements under test. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation, and there is no indication here that the skill offers locale selection or that the language restriction is justified.
The test emits multiple Chinese-language statements directly in console output, reinforcing a fixed-language experience. Because the file provides no mechanism for user language selection and no documented justification for the locale constraint, this fits the language-policy concern described by SQP-3.