Security audit

jiusansqmy

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese political-document drafting aid with narrow markdown-only behavior and no evidence of code execution, persistence, credential access, or exfiltration.

Install this if you want a Chinese-language template for formal 九三学社社情民意 drafting. Be aware that it may activate on broad related keywords and push outputs toward a strict official style, so users should explicitly ask for another format or language when they do not want that workflow.

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger is defined by broad topical keywords such as '九三学社', '社情民意', '建言献策', and '参政议政', so the skill may activate for casual discussion, analysis, or unrelated references rather than an explicit request to use this workflow. Unintended activation can override user intent and steer outputs into a rigid political-document drafting mode, which is especially risky because the skill imposes strong formatting and stylistic constraints.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill states that outputs 'must strictly follow' official formatting norms and formal government-document style, without indicating that the user can opt out or request a different register. This can cause the agent to substitute the skill author's preferred style for the user's actual request, reducing user control and potentially producing inappropriate or biased outputs when the user only seeks general help, critique, or informal guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file is entirely written as a Chinese sample document and presents the content as a fixed-format exemplar, with no indication that other languages are supported or that the user can opt into the locale. Under the policy for natural-language violations, forcing a specific language without user choice is in scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The title specifies a Chinese writing guide for 九三学社, which imposes a specific language/locale context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified.
Content: No source excerpt is available for this finding.