Security audit

Receiving Code Review

Security checks for vulnerabilities and agentic risk

Overview

This skill gives process guidance for handling code review feedback and does not contain hidden execution, persistence, or data exfiltration behavior.

Install this only if you want the agent to use a stricter, less deferential style when handling code review feedback. If it uses GitHub replies, review the exact comment before posting because that action would use your GitHub account permissions.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The manifest describes a behavioral/process skill for rigorously receiving code review feedback before implementation. Lines L203-L205 introduce a concrete operational capability for posting GitHub review replies via gh api, which goes beyond the stated purpose of evaluating feedback and into tool-specific remote interaction.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.