Security audit

Code Review Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AI code-review skill with no evidence of hidden execution, persistence, credential access, or destructive behavior, though users should treat submitted code and generated reports as sensitive.

Install only if you are comfortable sending reviewed code to whichever LLM implementation you configure. Do not submit proprietary code, secrets, or regulated data unless your LLM provider and logging environment are approved, and do not rely on the report as a sole security gate because source-code comments may influence LLM output.

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: index.js:69
Finding: Untrusted Reviewed Code Can Hijack LLM Review Instructions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill sends user-supplied source code to an LLM via this.manager.coordinate(task) after embedding the full code into prompts, but there is no built-in disclosure, consent flow, or data-handling warning. This can expose proprietary code, secrets, or regulated data to an external model provider, especially in a code-review tool where users may submit sensitive repositories.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The example prints both the full source code under review and the generated review report directly to stdout, which can expose sensitive code, secrets embedded in code samples, or security findings to terminal logs, CI logs, or shared consoles. In this skill's context, the reviewed input is arbitrary user-supplied code, so the example normalizes potentially unsafe disclosure behavior even though it appears intended only as a demo.
Content: No source excerpt is available for this finding.