ClawHub
Back to skill

Security audit

code-review

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PR review helper that inspects code and may use GitHub, Copilot, and subagents; no hidden install, persistence, or exfiltration behavior was found.

Use this skill when you are comfortable with an agent reading PR diffs and repository context, invoking subagents, and using your GitHub CLI session to request a Copilot review. Prefer invoking it explicitly, and review any prompt before approving pushes or issue creation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is intentionally broad: phrases like "review this PR" or similar common review language can cause the skill to auto-invoke in many ordinary conversations. That creates an overbroad activation surface where the agent may begin PR-review workflows, including repository inspection and GitHub actions, when the user did not explicitly intend to invoke this specific orchestration skill. In this skill, that risk is somewhat mitigated by confirmation gates for pushes and issue creation, but it still increases the chance of unintended tool use and external-side-effect setup.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.