Security audit

Code Craftsmanship

Security checks for vulnerabilities and agentic risk

Overview

This is a coding-style guidance skill that is broad but disclosed and does not add hidden execution, persistence, credential access, or data movement.

Install this if you want a coding agent to consistently follow stricter engineering discipline. Be aware that it is designed to apply broadly across normal development conversations, so users who want opt-in-only behavior may prefer a narrower activation policy.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill declares itself "active by default" for a wide range of tasks including writing code, debugging, code review, explanation, and architecture discussion. This broad activation description lacks narrow trigger constraints or exclusion conditions, increasing the chance of unintended invocation during ordinary engineering conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.