Back to skill

Security audit

freelance invoice tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly built for invoice tracking, but it can automatically contact clients about payments without enough confirmation and control safeguards.

Review this carefully before installing. Use least-privilege Google credentials, verify all client contact fields, keep reminder sending in preview/approval mode if possible, and avoid unattended cron sending until you have clear limits, logs, and a way to pause all outbound reminders.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly promises autonomous email and WhatsApp payment follow-ups, which can cause the agent to contact third parties without a just-in-time confirmation or a prominent user warning. In a billing context, mistaken reminders, misdirected messages, or overly aggressive cadence can harm client relationships and disclose invoice status or payment pressure to unintended recipients.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill processes sensitive personal and financial data including client names, emails, WhatsApp numbers, invoice amounts, GSTIN, bank account numbers, and UPI IDs, yet it provides no explicit privacy, retention, or data-handling warning. In this context, the combination of payment data and contact automation increases the risk of unauthorized disclosure, misuse of financial details, and privacy violations if the sheet, logs, or outbound messages are mishandled.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description frames the skill specifically for 'Indian freelancers' and embeds India-specific assumptions such as GST, INR, WhatsApp usage, and IST. Under the language/locale policy, locale-specific targeting should be clearly justified or presented as an explicit regional specialization rather than an implied default for all users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.