Back to skill

Security audit

PR Review Loop

Security checks for vulnerabilities and agentic risk

Overview

This skill is an instruction-only GitHub PR helper whose write access and polling behavior are disclosed and aligned with its review-loop purpose.

Install only if you are comfortable letting the agent make commits, push to the PR branch, resolve review threads, and monitor CI for the target repository. Prefer existing GitHub MCP/CLI auth over pasting tokens, scope any token to the intended repo and branch, and require explicit caution around force-with-lease or history rewrites.

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.