Security audit

classical-chinese

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small text-formatting helper that compresses replies into Classical Chinese, with no code execution, persistence, credential access, or data movement.

Install this only if you intentionally want replies compressed into Classical Chinese. For debugging, legal, medical, safety, or other detail-sensitive tasks, disable it or explicitly ask for normal-language clarity because compression may reduce readability.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Natural-Language Policy Violations

High

Confidence: 93% confidence
Finding: The skill states that token saving is the primary goal and readability may be sacrificed, which effectively forces a compressed language style once triggered. This is risky because it can omit qualifiers, steps, or warnings, increasing the chance of user misunderstanding, especially for technical guidance, troubleshooting, or safety-relevant instructions.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger description is broad enough to activate on common requests like 'save tokens' or 'be concise,' which can cause the skill to apply unexpectedly. Because the skill changes response style globally toward compressed classical Chinese, accidental activation can degrade clarity and interfere with safe, precise communication in technical or high-risk contexts.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file defines compression rules entirely as mappings from modern Chinese to Classical Chinese, with no indication that language transformation is optional or scoped to users who explicitly want Chinese output. That creates a natural-language policy concern because it prescribes a specific language/locale behavior without user opt-in or documented justification.

Static analysis

No suspicious patterns detected.