Back to skill

Security audit

Tax Document Deduction Organizer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only tax-record organization skill with broad triggers, but no hidden code, persistence, or data-moving behavior was found.

Before installing, be aware that this skill is meant for organizing tax records and may lead you to discuss financial documents. Use summaries or redacted extracts where possible, avoid sharing SSNs, account numbers, full tax IDs, or full unredacted records unless truly necessary, and rely on a qualified tax professional for filing or legal tax advice.

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
  • 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 (12)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README explicitly targets organization of income statements, receipts, deductions, and tax packets, all of which commonly contain highly sensitive personal and business financial information. Without any warning about minimizing, redacting, or carefully handling this data, users may be prompted to disclose unnecessary PII or financial records, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger sentences are broad, repetitive, and loosely scoped, which can cause the skill to activate for generic tax or workflow requests that may not actually require this specific capability. In a system handling sensitive financial topics, overbroad activation increases the chance of collecting or organizing personal tax data unnecessarily or in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This file is entirely in Simplified Chinese and presents the skill usage instructions in that locale without stating that language selection is optional. Under the policy, locale-specific guidance should either offer the user a choice or clearly justify the restriction.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad and map to common tax-help requests, which increases the chance this skill activates when a user did not explicitly intend to invoke it. In an agent ecosystem, overbroad invocation can cause the skill to intercept sensitive financial workflows and shape outputs or collect context unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says to use the skill for broad categories like business-and-operations, tax documents, deductions, receipts, estimated taxes, or any practical workflow or analysis support. That scope is wider than the concrete tax-packet organization use case and can cause the agent to invoke this skill for unrelated or only loosely related requests, leading to inappropriate handling, lower-quality guidance, or accidental collection/processing of sensitive financial information outside intended boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are generic terms that appear in many ordinary conversations, especially 'receipts' and 'business-and-operations.' Broad triggers increase the chance of accidental activation in contexts where the skill is not appropriate, which can misroute the conversation and expose users to tax-oriented workflows when they did not request them.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example trigger sentences use highly generic phrasing like 'Help me' and 'I need a practical workflow,' which overlaps heavily with normal user language. If downstream routing relies on these examples, the skill may be selected too often for generic assistance requests, causing scope confusion and potentially mishandling sensitive financial discussions under an ill-fitting workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and use conditions are scoped to a very broad set of business and tax-related requests, which increases the chance of unintended invocation on loosely related prompts. Over-broad routing can cause the wrong skill to handle sensitive financial workflows, leading to inappropriate guidance, unnecessary collection of financial details, or interference with safer, more specific skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The example trigger phrases are vague and resemble normal conversational language, making accidental activation more likely. In a tax context, accidental invocation is more sensitive because users may disclose personal or financial information to a skill that was selected based on an imprecise match rather than clear intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The default prompt is broad and truncated, covering a wide range of tax and business-related requests without clear boundaries. This can cause the skill to be invoked in unintended contexts, increasing the chance of handling sensitive financial data or providing tax-related guidance when a more specific or better-scoped skill should be used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance does not clearly define when the skill should and should not run, leaving activation boundaries ambiguous. In a tax-document context, this is more sensitive because users may reveal personal or financial records, so mistaken invocation can expose or mishandle sensitive data and produce irrelevant guidance in place of the correct workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger sentence is broad enough to match ordinary user language about taxes and practical workflows, which can cause the skill to activate outside a clearly bounded context. Over-broad activation increases the chance of unintended routing, confusing responses, and accidental handling of sensitive financial information when a more appropriate skill or narrower flow should have been used.

Content

No source excerpt is available for this finding.