Security audit

Attorney

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only attorney navigation skill with no executable code or special permissions, but users should treat its legal guidance as informational and verify deadlines locally.

Install only if you want general help deciding when to contact an attorney, preparing for consultations, and organizing legal questions. Do not rely on it for legal advice, exact filing deadlines, or jurisdiction-specific procedure; verify dates on official documents and consult a licensed attorney for significant, urgent, or contested matters.

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 (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: These examples present legal guidance in a directive, authoritative style without a clear warning that the skill is informational only and not a substitute for qualified legal advice. In a legal-help skill, users may reasonably rely on the outputs for real disputes, deadlines, fees, or representation decisions, increasing the chance of harmful action based on incomplete or jurisdiction-specific guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The instruction to run the skill when "any legal situation begins" is very broad, and the example prompt could cover a wide range of everyday disputes or concerns without clarifying what does not qualify. The file does not provide negative examples or scope limits to prevent unintended invocation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill presents legal timing guidance as generally applicable without stating jurisdictional limits, even though statutes of limitations, preservation duties, and procedural expectations vary significantly by country and region. In a legal-assistance context, users may rely on this as authoritative and make time-sensitive decisions based on assumptions that are wrong for their locale.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction to run immediately when "any legal document arrives" is expansive and may include low-importance or routine documents. Although urgent document examples are listed later, the trigger itself does not constrain scope or identify documents that do not require immediate use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill gives concrete response timelines for summonses, motions, and other legal documents without qualifying them by jurisdiction, court, or document type. In a legal skill, this is especially dangerous because users may miss actual deadlines or misunderstand urgency, leading to default judgments, waived rights, sanctions, or other serious legal harm.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list contains broad phrases such as 'legal advice', 'legal issue', 'court', and 'legal document' that are likely to match many general-purpose conversations. This can cause the skill to activate outside its intended scope, increasing the chance of inappropriate routing, over-assertive legal guidance, or unnecessary collection of sensitive legal information from users who did not explicitly ask for attorney-focused help.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The phrase "While a legal matter is ongoing" does not specify whether the weekly check applies only to represented matters, active litigation, or any unresolved legal concern. Without boundaries or exclusions, users may invoke it in situations where the cadence is unnecessary or unclear.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.