Security audit

Business Doc Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward business-document template skill, with some privacy and activation-scope caveats but no evidence of hidden execution or data exfiltration.

Install only if you want an agent to help draft business documents. Review legal documents with a qualified professional, confirm financial figures before use, and avoid saving confidential client or payment details in shared workspaces unless that storage location is appropriate.

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes broad natural-language phrases like 'generate document' and 'business document' that can match many ordinary user requests, causing the skill to activate outside its intended scope. In a skill that generates contracts, invoices, and other potentially sensitive business artifacts, over-activation increases the chance of collecting or storing personal, financial, or legal data when the user did not explicitly intend to use this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation section contains a catch-all condition ('Any combination of the above with customization needs') that does not meaningfully constrain when the skill should run. This ambiguity can cause the agent to invoke the skill for loosely related requests, which is risky because the skill solicits and may retain sensitive business, personal, and financial information.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill instructs storage of generated document templates in the user workspace but does not clearly warn that the content may contain sensitive personal, financial, or legal data and should be reviewed before persistence. This can lead to accidental retention of confidential information in shared or insufficiently protected storage locations, especially for invoices, contracts, NDAs, and proposals.
Content: No source excerpt is available for this finding.