Security audit

Sue

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only lawsuit guidance skill with no hidden code, install hooks, persistence, or data access, but users should not treat it as legal advice.

Before installing, understand that this skill may give confident-sounding litigation guidance. Use it for general organization and issue spotting only, and verify deadlines, filing rules, settlement choices, and collection steps with a licensed attorney, legal aid, or the relevant court.

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)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The examples provide case-specific legal guidance and procedural recommendations without any visible disclaimer that the information may vary by jurisdiction or that it is not a substitute for advice from a licensed attorney. In a legal-dispute skill, users may reasonably rely on the output to make time-sensitive decisions about filing, settlement, limitation periods, or judgment enforcement, increasing the risk of harmful reliance.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This skill provides deadline-sensitive litigation guidance and encourages users to take concrete steps in active disputes without clearly warning that the content is not legal advice and may not account for jurisdiction-specific rules. A user could rely on the guidance, miss a filing deadline, waive rights, make harmful statements, or delay consulting counsel, causing significant legal prejudice.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list includes very broad, high-frequency phrases such as "sue," "lawsuit," and "damages," which can cause the skill to activate in many contexts beyond a user explicitly seeking this legal-assistance workflow. Unintended activation is especially sensitive here because the skill concerns legal disputes, where irrelevant or premature guidance could influence consequential decisions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill provides self-representation and filing guidance for small claims court without an explicit warning that legal procedures, deadlines, and jurisdiction-specific rules can materially affect a user's rights. Users may rely on the skill as a substitute for qualified legal advice, leading to missed claims, procedural errors, or harmful admissions with real legal consequences.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.