Security audit

litigation response

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language litigation response drafting skill that handles sensitive case details, but its behavior is disclosed, purpose-aligned, and limited to markdown guidance/templates.

Before using this skill with real litigation materials, redact unnecessary identifiers and avoid entering exact settlement bottom lines unless needed. Treat outputs as drafting support and have a qualified legal professional review strategy and filings.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly instructs extraction and structuring of highly sensitive personal and litigation data, including identity numbers, addresses, contact details, and case materials, but it does not provide a clear privacy/confidentiality warning, minimization guidance, or handling constraints before processing. In a legal-defense context, this increases the risk of unnecessary collection, oversharing to the model, and downstream disclosure of privileged or regulated information.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The template explicitly solicits highly sensitive personal and case-identifying data, including ID numbers, addresses, legal representatives, and contact details, but provides no warning, minimization guidance, or handling precautions. In a litigation-support skill, users may paste real client or party information, creating unnecessary privacy, confidentiality, and legal-professional-risk exposure if the data is stored, shared, or processed beyond what is strictly needed.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The template asks for negotiation posture, acceptable settlement amount, and bottom-line terms—information that is strategically sensitive in active litigation. If disclosed to unintended parties, logged insecurely, or reused outside the user's control, it could materially weaken the user's bargaining position and directly harm legal outcomes.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file is entirely written in Chinese, and there is no indication that the skill offers a language choice or that the Chinese-only constraint is intentionally limited to a specific regional or compliance context. Under the policy, language constraints should either be optional for the user or clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The natural-language instructions and outputs are written exclusively in Chinese, which can amount to a forced language choice if organizational policy requires language neutrality or user opt-in. The file does not state that the skill is limited to a Chinese-speaking or PRC-specific legal workflow, nor does it offer an alternative language option.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The template is presented only in Chinese and does not state that the language is optional, user-selected, or limited to a specific Chinese-language legal workflow. The policy requires flagging natural-language content that forces a specific language without user opt-in unless the locale constraint is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The entire skill file is written in Chinese and does not indicate that language selection is optional or limited to a China-specific workflow. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.