Security audit

Zoom Out

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown guidance skill for understanding code architecture and does not add executable code, persistence, credential access, or hidden behavior.

Install this if you want a reusable prompt pattern for architecture overviews. Expect it to inspect relevant project files and call relationships when invoked, but the reviewed artifact does not execute code, install dependencies, persist state, or handle credentials.

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

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The 'Trigger this when' section relies on subjective phrases like 'unfamiliar codebase,' 'bigger picture,' and 'need a map,' which are broad and interpretation-dependent. Although the anti-patterns add some limits, the file does not define specific trigger phrases or clear exclusion boundaries sufficient to avoid unintended invocation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.