T09 · Insecure Skill Coding Practices
Warning
- Location
references/material-checklist.md:82- Finding
Plaintext Distribution of Unrestricted Test-Account Credentials
- Content
View full analysis
- Remediation
View remediation
Security audit
算法备案助手
Security checks for vulnerabilities and agentic risk
Overview
This skill is mostly a coherent China CAC filing assistant, but it tells users to prepare unrestricted test-account credentials in documents without adequate safeguards.
Review the credential-handling parts before installing or using this skill. If you use it, treat any reviewer accounts as least-privilege, isolated, short-lived accounts; do not store passwords in shared filing documents or cloud docs unless your organization has an approved secure transfer process. Also verify current CAC requirements with counsel or official sources because the skill gives authoritative regulatory guidance.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill description, title, features, and trigger phrases are entirely in Chinese, indicating the skill is intended to operate in a single language/locale without any explicit opt-in or alternative. Under the policy, language restrictions should either offer user choice or be clearly documented as a justified locale-specific constraint.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list contains broad terms like '安全评估报告', '算法合规', and 'beian.cac' that can match many ordinary compliance or regulatory questions outside the narrow CAC filing workflow. This can cause the skill to activate unexpectedly, intercept unrelated user intent, and steer users into a specialized compliance process with authoritative-sounding guidance that may be inapplicable or overbroad.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This markdown file is entirely written as prescriptive guidance in Chinese and includes fixed Chinese labeling examples such as '【AI 生成】', but it does not state that the skill is region-specific or that users may choose another language. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill content is entirely written in Chinese and provides no indication that users may choose another language or that the Chinese-only requirement is an explicit, justified locale constraint. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The document title and entire template are written exclusively in Chinese, and the framework assumes Chinese-language output throughout without any note that language selection is optional. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified as region-specific.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The instructions position the skill exclusively around China CAC processes and are written entirely in Chinese, with no indication that users can choose another language or locale. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern unless the constraint is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire document is written in Chinese and presents China-specific legal and regulatory guidance without offering any language choice or indicating that the locale is intentionally limited. Under the policy rule for natural-language violations, this can be considered a language/locale constraint that is not explicitly opt-in or justified within the file itself.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The entire checklist is written only in Chinese and presents requirements such as Chinese-citizen status and China-specific filing materials without any indication that the language choice is optional or that the document is explicitly limited to a China-only audience. Under the policy rule, a fixed language/locale can be a natural-language policy issue unless the regional constraint is clearly documented and justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
This markdown file presents all instructions and compliance guidance solely in Chinese, and it does not indicate that the skill is limited to Chinese-speaking users or a China-specific audience. Under the policy rule for language/locale, forcing a single language without user opt-in can be a natural-language policy violation.
- Content
Static analysis
No suspicious patterns detected.