Back to skill

Security audit

update-cursor-settings

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives instructions for editing Codex/VSCode user settings and does not include hidden code, network access, credential handling, or automatic execution.

Install this only if you want an agent to help edit global Codex/VSCode user settings. Review the exact setting key and value before applying changes, because user settings persist across projects and may require an editor reload.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broadly scoped to modify any settings.json values whenever the user wants to change editor settings or preferences. Overly broad activation criteria can cause the agent to invoke this skill in situations where changing persistent global configuration is unnecessary or risky, increasing the chance of unintended state changes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown guidance repeats ambiguous invocation language like using the skill when the user wants to change preferences or any settings.json values, without guardrails on confirmation or scope. This can lead to unnecessary or overbroad use of a persistent configuration-writing skill, which is dangerous because it alters global IDE behavior beyond the current task.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
1. Parse the existing JSON (handle comments - VSCode settings support JSON with comments)
2. Add or update the requested setting
3. Preserve all other existing settings
4. Write back with proper formatting (2-space indentation)

### Example: Changing Font Size

Static analysis

No suspicious patterns detected.