Back to skill

Security audit

PR Context Diagram

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent pull request writing workflow with disclosed repository access and no hidden execution or persistence.

Use it for repositories and PRs you authorize the agent to access and update. Review descriptions for private logs, identifiers, URLs, and unsupported verification claims before publication. The full artifact was manually reviewed; live GitHub operations were not exercised.

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
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose is not represented by the supplied code. If executed as shell, the line invokes test with invalid arguments rather than creating or updating a PR description. No undeclared resource access or other substantive capability is evident.

Content

No source excerpt is available for this finding.