Security audit

compatsy

Security checks for vulnerabilities and agentic risk

Overview

The skill provides proportionate product compatibility and price checks, with disclosed affiliate links and a limited correction-reporting workflow.

Product queries and corrections go to compatsy; keep personal or confidential information out of corrections. Setup saves two remote server connections, and purchase links may earn compatsy a commission.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The workflow submits the user's correction to a third-party service without a privacy warning.

Medium

Category: Output Handling
Confidence: 92% confidence
Finding: The skill instructs the agent to send the user's claim to compatsy through report_issue whenever the user disputes a fact. Although it explains that reports do not edit facts, it does not warn that the user's feedback will be transmitted to an external service.
Content: No source excerpt is available for this finding.