Back to skill

Security audit

subscription-renewal-notices

Security checks for vulnerabilities and agentic risk

Overview

The skill supports supervised renewal-notice drafting without automatic sending, but its calculator is incomplete and the optional Windows app requires separate assessment.

Use this as a supervised drafting aid. Verify amounts against billing records and independently check current legal requirements before delivery. Do not treat calculation.md as a calculated total or compliance approval. Assess the optional unsigned Windows app separately; its supplied hash does not establish 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code is materially narrower and different in purpose from the declared drafting-and-checking workflow. Its only active workflow parses six numeric fields and writes a static Markdown report. The guardrail text does not constitute enforcement or validation. Local file access supports that reporting workflow and is not itself an unrelated capability; no network access or email sending is implemented.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
## The job

Renewal notices go out as a receipt with no warning that the price changes, so cancellations spike and refund requests follow.

## What you get

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 documented renewal calculator only echoes inputs and a formula; it never computes the renewal amount.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script claims to calculate a renewal amount but only writes parsed inputs and the formula, leaving downstream users or agents without a computed, verified total. In a billing-notice workflow, this integrity defect can lead to guessed or incorrect renewal amounts; silently converting malformed inputs to zero further increases that risk. The script does not send notices, and its billing-system verification guardrail limits direct impact, but neither compensates for the missing calculation.

Content

No source excerpt is available for this finding.