Security audit

fencha-thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese problem-structuring guidance skill with broad triggers but no code execution, data access, persistence, or hidden behavior.

Install this if you want a Chinese-language framework for clarifying messy problems. Be aware it may trigger in ordinary uncertainty-related conversations, and non-Chinese users may find it unsuitable unless the agent translates or adapts it.

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

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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is extremely broad ('messy or unclear', 'unsure how to handle a situation', 'communicate something more effectively'), which can cause the agent to invoke this skill in many ordinary conversations. Over-broad activation increases the chance that this skill overrides more appropriate domain-specific or safety-constrained behaviors, leading to misrouting and unreliable responses.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill content is written entirely in Chinese and provides no user-choice mechanism or justification for enforcing that language. If auto-invoked for users who did not request Chinese, it can degrade comprehension, cause task failure, and interfere with safe communication in sensitive contexts such as complaints or high-stakes guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description activates on very broad situations like feeling unclear, messy, or needing to communicate better. In an agent system, such generic criteria can cause the skill to be invoked across many unrelated tasks, increasing prompt-surface area and making routing less predictable. The content itself is not overtly harmful, but overbroad activation can override more appropriate specialized skills or inject unsuitable conversational behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Several trigger keywords are common everyday phrases such as '脑子一团乱' or '不知道该先做哪个', which are likely to appear in many normal conversations. This can lead to unintended invocation, causing the agent to switch into this framework when the user did not ask for it and potentially derailing task execution or exposing the system to unnecessary instruction mixing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: All user-facing instructions, examples, and guidance are presented in Chinese, and the file does not state that the skill is limited to Chinese-speaking users or provide an opt-in language choice. This can violate language/locale policy when a skill effectively forces a specific language without user selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The natural-language content in the prompts and expected outputs is entirely in Chinese, with no indication that users may choose another language or locale. Under the policy rule, a skill that effectively constrains interaction to a specific language without documented opt-in can be considered a locale/language policy issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.