Back to skill

Security audit

invoice-chasing-sequence

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill keeps invoice reminders under your control, but its script produces only a basic schedule rather than the promised drafts.

Expect a basic scheduling scaffold and review all customer-facing material yourself. Choose an output folder where replacing plan.md is acceptable. Treat the optional Windows app as a separate software decision; this verdict does not establish that executable's safety.

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
98% confidence
Finding

The code shares the declared invoice-collection theme but lacks its substantive promised functionality. Each scheduled entry contains only the initial focus or 'next block', rather than a collection touch with messaging and dispute handling. Local input reading and output writing are ordinary supporting operations; no undeclared sending, network access, or other unrelated capability is evident.

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 generated plan lacks the invoice follow-up content promised by the manifest.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a 30/60/90-day invoice follow-up cadence with email drafts, a call script, and a dispute path for each touch. L83–L93 instead generate weekly dates labeled with an initial focus or 'next block', followed by generic guardrails; no email drafts, call scripts, or dispute paths are produced.

Content

No source excerpt is available for this finding.