Security audit

tang poetry challenge

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese Tang poetry quiz skill with local data and no evidence of hidden or unsafe behavior.

Users should expect a Chinese-only educational quiz that runs local Python scripts over bundled poetry data. The main consideration is language fit, not security exposure.

A.I.G

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (5)

Lp3

Medium

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

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The natural-language content in the description, headings, workflow, and examples consistently forces Chinese as the interaction language. Under the policy criteria, this is a language/locale constraint without user opt-in or an explicit justification that the skill is intended only for a Chinese-language audience.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: This code presents all user-facing prompts, feedback, and scoring messages exclusively in Chinese. The policy requires flagging language/locale constraints when the skill forces a specific language without user opt-in, and this file does not offer any alternative language selection or explain a region-specific requirement.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The class docstrings, user-facing tips, analyses, and explanations are all fixed in Chinese, which imposes a specific language on users. The file does not provide any opt-in, fallback, or justification that this skill is intentionally limited to a Chinese-speaking or region-specific context.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: This manifest-style data file contains only Chinese titles, authors, and poem lines, with no indication that the skill is region-specific or that users can opt into Chinese-only content. Under the stated policy, forcing a specific language without user choice can be a natural-language policy concern.

Static analysis

No suspicious patterns detected.