Back to skill

Security audit

Recipe Label And Archive Emails

Security checks for vulnerabilities and agentic risk

Overview

This is a small Gmail productivity recipe that clearly tells the agent to label and archive selected messages, with no hidden code or persistence.

Install only if you want Codex to help change Gmail labels and archive selected messages. Before running the modify steps, check the search results, message IDs, and label ID, because archiving removes messages from the inbox even though it does not delete them.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill gives direct instructions to search, relabel, and archive Gmail messages, which changes mailbox state and can hide messages from the inbox without any explicit warning, confirmation step, or safety guidance. In a productivity recipe this behavior is expected, but the lack of guardrails increases the risk of accidental bulk modification of important emails or concealment of messages the user did not intend to archive.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.