Security audit

Laundry Care Symbol Decoder

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only laundry care helper with no executable code, network access, credential use, or persistence, though its triggers and version metadata could be tightened.

Before installing, expect the skill to help with clothing tag symbols and cautious care sheets only. Review broad trigger phrases if accidental activation matters in your environment, and note the minor version mismatch for publisher cleanup.

A.I.G

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

SkillSpector

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 (4)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: Several trigger keywords are broad natural-language phrases such as 'washing instructions' or 'how to wash this garment', which can match ordinary user requests and cause the skill to activate when the user did not explicitly intend to use it. In a prompt-flow skill, this can lead to misrouting, user confusion, or unintended disclosure of garment details into the skill context, though the overall security impact is limited because the skill is local, document-only, and has no API or code execution.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The metadata states "Language is `en`", and the clean-scan section reinforces an English-only constraint. This can constitute a language policy restriction when no user opt-in, alternative language support, or justification is provided.

Vague Triggers

Low

Confidence: 78% confidence
Finding: This markdown file includes an example user utterance for invoking the skill, but it does not provide explicit negative examples or tighter trigger constraints. While the phrase is somewhat domain-specific, the file does not clearly distinguish when the skill should activate versus when a general clothing-care question should not trigger it.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: The manifest sets `"language": "en"`, which indicates a fixed language choice. Under the stated policy, forcing a specific language can be a natural-language policy issue when the skill does not offer a user choice or document a justified region-specific constraint.

Static analysis

No suspicious patterns detected.