Security audit

Legal Settlement Evaluation Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only legal workflow skill, but one example gives specific settlement advice that conflicts with its own stated limits.

Review this skill carefully before installing for legal workflows. It has no code-execution or data-access risk, but users should not rely on its concrete settlement amounts or insurance recommendations as legal advice; decisions should be checked with qualified local counsel.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill explicitly states it should not advise acceptance and should provide frameworks rather than legal conclusions, yet Scenario 4 gives a concrete recommendation, negotiation range, and conditional advice about when to settle or use insurance. In a legal-decision-support context, this can cause users to rely on individualized quasi-legal advice despite the stated limitations, increasing risk of harmful financial or legal outcomes.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The overview promises descriptive workflow support only, but the included example content contradicts that boundary by offering individualized compensation guidance. This inconsistency is dangerous because it can defeat user safety expectations and encourage reliance on the skill for legal judgment rather than structured issue-spotting.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file declares language: en at L005 and later states the package is 'English-first' at L101, but Scenario 4 is entirely in Chinese. This introduces a language/locale inconsistency in the skill content without offering the user a language choice or documenting a justified locale exception.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The acceptance criteria state that SKILL.md and README.md are 'English-first,' which is a natural-language constraint. Under the policy rules, forcing a specific language without user opt-in or a clearly documented justification can be a policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The package rules repeat that the package must remain 'English-first,' reinforcing a mandatory language constraint. This appears to require a specific language for the skill materials without indicating user choice or a region-specific compliance need.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest sets the skill language to "en", which is a natural-language locale constraint. Under the policy, forcing a specific language is a violation unless the skill offers user choice or clearly documents a justified region- or compliance-specific limitation, which is not present here.
Content: No source excerpt is available for this finding.