Security audit

review-github-pr

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed GitHub pull request review skill that uses GitHub tools for its stated purpose and requires user confirmation before running checks or posting reviews.

Install this only if you are comfortable letting the agent use your GitHub CLI authentication to read PR data, inspect local repository files, run a confirmed validation command, and post a confirmed review. Review the generated draft before approving any GitHub action.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 96% confidence
Finding: The skill clearly instructs the agent to use both shell and network-capable tools (`gh`, `git`, cloning repos, calling the GitHub API), but it does not declare permissions or otherwise constrain those capabilities. In a skill system that relies on declared permissions for review, policy enforcement, or user consent, this creates a real security gap because the skill can fetch remote content and execute local commands without an explicit capability contract.

Static analysis

No suspicious patterns detected.