Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 评估引擎脚本移至 scripts/evaluation-engine.js
Security audit
Skill Quality Assurance
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local quality-assessment helper that reads skill files and writes a Markdown report, with no evidence of hidden execution, network access, credential use, or persistence.
Install only if you are comfortable with a Chinese-language quality checker that reads the skill directory you point it at and writes a local Markdown report. Treat its scores as heuristic guidance, not a definitive security or marketplace approval decision, and choose the output path carefully because an existing same-named report could be overwritten.
Vulnerability Patterns
- 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
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (11)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 评估引擎脚本移至 scripts/evaluation-engine.js
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 评估引擎脚本移至 scripts/evaluation-engine.js
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 评估引擎脚本移至 scripts/evaluation-engine.js
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The manifest description and primary user-facing headings are written entirely in Chinese, and the usage examples also assume Chinese-language interaction. This creates a language/locale constraint without any opt-in, alternative language option, or documentation that the skill is intentionally region-specific.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This markdown template is entirely written in Chinese and provides fixed Chinese section headings and labels, which constrains generated evaluations to a specific language. The file does not offer an opt-in/opt-out mechanism or state that the skill is intentionally region-specific, so it appears to violate the language/locale choice policy.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This markdown reference document is written entirely in Chinese and presents the evaluation standard as the skill's canonical guidance without offering an alternative language, opt-in, or explanation for a locale-specific requirement. Under the policy, forcing a specific language without user choice is a natural-language locale violation.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The manifest promises automated six-dimensional evaluation of skills, suggesting meaningful assessment across technical depth, cognition, orchestration, evolution, market validation, and user experience. However, the C/O/E/M/U evaluators mostly score by checking whether specific words appear in SKILL.md, which materially differs from evaluating actual skill capabilities or evidence for those dimensions.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This .js code contains multiple user-facing console messages in Chinese, including usage instructions, errors, and success output. Because the skill does not offer language selection or explain that it is intentionally region/language-specific, it appears to enforce a specific locale without user opt-in.
- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The manifest describes an assessment assistant, which primarily implies analyzing skills and producing evaluation results. In this file, the CLI implementation goes beyond in-memory evaluation and persists a Markdown report to a user-specified filesystem location, which is an additional side effect not reflected in the manifest description.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file presents its title and content in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the natural-language policy rules, forcing a specific language without user opt-in is a policy concern.
- Content
Static analysis
No suspicious patterns detected.