Security audit

Legal Risk Assistant

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its China legal-triage purpose, but it embeds off-platform upgrade prompts into legal answers and lacks clear privacy guidance for sensitive legal materials.

Before installing, treat this as a review-needed legal helper: avoid sharing unnecessary personal, financial, employer, customer, or case-identifying details, and be aware that the skill may steer deeper requests toward contacting the author for paid Pro / Business access outside the platform.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:32
Finding: Mandatory Commercial Promotion Injected into Legal-Assistance Responses
Content: View full analysis
If you need deeper clause rewriting, a more complete template library, an enterprise version, or customized delivery, contact the author to upgrade to the Pro / Business version. **English** > Need deeper clause rewriting, richer templates, or a business-use version? Contact the author for Pro / Business access. ``` ### Technical Analysis The controlling Skill instructions establish a commercial response branch that activates when a user requests deeper legal assistance. In particular, line 42 directs the Agent to explicitly state that the free version is limited and to promote contacting the author for paid Pro or Business access. This is not merely marketplace metadata. Because the instruction resides in `SKILL.md`, it affects the Agent at runtime and can alter final user-facing responses. The provided promotional templates at lines 60-68 make the commercial insertion repeatable across contract review, labor-dispute analysis, and legal-document draftin ...[truncated 2117 chars]
Remediation: View remediation

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 (16)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The skill title and nearly all operating instructions are written as a China-focused assistant in Chinese, but the file does not explicitly offer users a language or locale choice for responses. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the constraint is clearly documented and justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file is entirely written in Chinese and provides only Chinese output templates and phrasing, with no indication that the assistant should detect or respect the user's preferred language. This can exclude or mislead users who interact in another language, and in a legal-triage context it increases the risk that users misunderstand cost estimates, assumptions, or limitations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The listing invites users to submit contracts, labor-dispute facts, lawsuit-cost questions, and draft legal materials, but it does not clearly warn that these inputs may contain highly sensitive personal, financial, employment, or case information. In a legal-assistance context, missing privacy guidance increases the risk that users will overshare confidential data, which can lead to exposure of personal or case-sensitive information through platform processing, retention, or misuse.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The release copy invites users to submit real contracts, labor-dispute facts, debt disputes, and draft-document needs, but it does not clearly warn that these materials may contain highly sensitive personal, financial, employment, and legal-strategy information. In a legal-assistant context, that omission can cause users to disclose confidential data without minimization or redaction, increasing privacy, confidentiality, and compliance risk.
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 presents all instructions and examples exclusively in Chinese, which can amount to a language-policy constraint if users are not given an opt-in or alternative locale. The file does not indicate that the skill is region-specific or that Chinese is required for a justified compliance or jurisdictional reason.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The file's natural-language content exclusively uses Chinese, which can amount to forcing a specific language without user opt-in under the stated policy. There is no indication that the skill is region-specific or that users may choose another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file presents all skill content in a single language and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. Under the policy rule for language/locale constraints, forcing one language without opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file presents all skill examples and usage guidance exclusively in Chinese, which can constitute a language/locale policy violation when no user opt-in or documented regional scope is provided. The file does not indicate that the skill is China-specific or that users may choose another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This markdown file presents all instructions, evaluation criteria, and conclusions exclusively in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-language or region-specific context. Under the policy, a forced language or locale without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file presents the skill content entirely in Chinese and does not indicate that the language was selected by the user or that alternatives are available. Under the policy rule for language or locale constraints, forcing a specific language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The title and all field labels are presented only in Chinese, which imposes a specific language on users. Under the policy, language constraints should either be optional/opt-in or clearly documented as justified for a region-specific use case.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The entire skill listing is written only in Chinese and repeatedly scopes the service to common Chinese civil and labor scenarios, but it does not explicitly state that the skill is Chinese-only or offer any user opt-in or language choice. Under the policy, forcing a specific language or locale without user choice can be a natural-language policy concern unless the 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: 91% confidence
Finding: This markdown file presents all instructions and templates exclusively in Chinese, and it does not indicate that the user can select another language or that the skill is intentionally limited to Chinese-language use. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file presents all instructions and output requirements exclusively in Chinese, which can amount to a language/locale policy constraint if users are not given an opt-in or alternative language. The file does not state that the skill is region-specific or that Chinese is required by design.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file contains user-facing skill acceptance criteria exclusively in Chinese, and nowhere indicates that the skill is China-specific or that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file is entirely written in Chinese and presents the skill evaluation content in that language without any indication that users may choose another language or that the skill is intentionally limited to a Chinese-only regional/legal context. Under the language/locale policy rule, a file that effectively enforces one language without opt-in can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.