Back to skill

Security audit

tax-season-organizer

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because its promised checks can miss missing tax forms and exposed taxpayer identifiers while reporting no problems.

Use redacted inputs and manually verify forms and taxpayer IDs. Do not rely on 'No flags' or assume reports mask identifiers. Request corrected detection and redaction before relying on this workflow, and assess the optional Windows app separately.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The reported implementation defects undermine checks that users are explicitly instructed to rely on for missing W-9s, taxpayer-ID mismatches, and unmasked identifiers. False negatives in this tax-document workflow could leave sensitive identifiers exposed or compliance tasks overlooked; however, the script was not supplied, so the reported code defects cannot be independently verified from SKILL.md alone.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The promised missing-W-9 and taxpayer-ID flagging is ineffective because regex rules are checked as literal substrings.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The rules contain regular expressions, but the scanner checks them using literal substring membership, so ordinary text describing missing W-9s, unresolved taxpayer IDs, overdue 1099s, or full SSNs will not trigger the intended flags. In this tax-document workflow, the resulting 'No flags' report can create false assurance and allow sensitive identifiers or compliance issues to pass unnoticed; the human-review disclaimer does not correct the broken detection.

Content

No source excerpt is available for this finding.