Back to skill

Security audit

Return Window Rescue Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only return-planning checklist skill with disclosed limits and no code, network, credential, or account access.

Before installing, understand that the skill may ask for shopping and return details such as order numbers, labels, receipts, and item locations. Provide only what is needed, redact unnecessary personal data, and independently verify store policies and deadlines before acting.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The acceptance criteria state 'No CJK characters. Documentation is English/ASCII only' and the manifest metadata is constrained to language=en. This is a natural-language locale policy constraint, and the file does not offer any user choice or explain a region-specific reason for forcing English-only behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are broad, everyday requests such as 'plan my returns' and 'organize my returns', which can cause the skill to activate unintentionally in general conversation. This is mainly a safety and UX issue rather than a direct security exploit, but unintended activation can surface private shopping or logistics details in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest sets "language": "en" with no indication that users may opt into another language or that the skill is intentionally limited to English for a documented reason. This can conflict with language/locale policy expectations requiring user choice or explicit justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.