Security audit

sinan-thinking-adapter-v4

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed teaching-style adapter with no code execution, external access, or hidden privileged behavior.

Install this only if you want the assistant to use a more structured, beginner-friendly teaching style by default. You can still ask for shorter, more direct, or differently formatted answers, and the skill itself does not add code, background processes, or external data access.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The skill description and later language rules set communication defaults such as preferred language style, sentence structure, and formatting without an explicit per-user opt-in. While not an exploit in the classic sense, this can steer model behavior in ways that override user preference, reduce autonomy, or create subtle prompt-priority conflicts when a user wants a different communication style.

Static analysis

No suspicious patterns detected.