Back to skill

Security audit

Restaurants

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local restaurant note-taking workflow with no executable code, network access, credential use, or hidden behavior.

Install this only if you want the agent to keep local Markdown notes about restaurants, meals, ratings, occasions, and dietary preferences in ~/restaurants/. Review what it saves if restaurant history or dining preferences are sensitive for you.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill activates on very broad, common conversation patterns such as any mention of a restaurant or returning from a meal. This can cause unintended invocation in ordinary chat, leading the agent to create or manipulate personal restaurant-tracking data when the user did not explicitly intend to use this skill.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
- Build cuisine and occasion lists over time

## What NOT To Do
- Recommend unsaved places without asking
- Forget dietary restrictions
- Over-organize — simple notes work

Static analysis

No suspicious patterns detected.