Security audit

Quality-Driven Development (QDD)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed coding workflow guide for tests, specifications, logging, and quality checks, with no executable payload or hidden persistence.

Before installing, expect this skill to make the agent follow a fairly strict test-first quality workflow, create SPEC documentation, run tests or coverage commands when available, and add logging to changed code paths. Users who do not want broad coding-task activation or mixed Korean/English guidance may want the publisher to narrow the trigger wording or translate the logging rules, but no hidden or malicious behavior was identified.

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 (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill advertises itself for essentially any coding task ('building features, refactoring code, fixing bugs, or any coding task'), which makes it eligible to activate in a very wide range of contexts. Overly broad activation increases the chance the agent will invoke this skill when a narrower or safer workflow would be more appropriate, creating unnecessary authority over development decisions and command execution.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The file includes a Korean-language core philosophy statement while the rest of the skill is in English, and the skill does not indicate that language selection is user-driven or optional. This can violate language/locale policy expectations when a skill imposes or assumes a language without user opt-in.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The logging table and rules contain substantial Korean-only guidance embedded in an otherwise English skill file. Because no locale constraint or user language preference is documented, the skill effectively imposes mixed-language instructions that may not be accessible to all users.

Static analysis

No suspicious patterns detected.