Back to skill

Security audit

Business Document Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward business document template generator, with local saving guidance that users should handle carefully.

Before installing, be aware that the skill may help draft documents containing client names, addresses, prices, payment terms, and legal language; confirm important figures and legal terms yourself, and only save generated documents in the workspace when you are comfortable retaining that information locally.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is broad enough to activate on common requests like general document writing or drafting help, which can cause the skill to engage unexpectedly. Overbroad activation can lead to unintended application of this skill's instructions, including persistence behavior and legal-document defaults, in contexts where the user did not request this specialized workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation logic includes an open-ended catch-all ('Any combination of the above with customization needs'), which lacks clear boundaries and makes over-activation more likely. In context, this is more dangerous because the skill also collects structured business data and instructs storage in the workspace, so accidental invocation may expose or retain more sensitive information than necessary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs storage of generated templates in the user workspace without a clear warning that content may persist locally. Because the documents may contain client identities, addresses, pricing, payment instructions, and contract terms, undisclosed persistence creates privacy and confidentiality risks.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill includes an instruction to store generated document templates in the user workspace even though its primary function is content generation, not persistence. This creates an unnecessary data-retention behavior that may save sensitive business, financial, or legal information without explicit user consent or clear disclosure.

Content

No source excerpt is available for this finding.