ClawHub
Back to skill

Security audit

Receiving Code Review

Security checks for vulnerabilities and agentic risk

Overview

This is a code-review workflow guidance skill with no bundled executable code, persistence, or hidden data access.

Install this if you want stricter, verification-first code review behavior. Be aware it will discourage polite gratitude-style acknowledgments, and any actual GitHub replies should still be user-directed before posting.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

These instructions ban phrases like "Thanks for catching that" and even "ANY gratitude expression," which imposes a specific interpersonal communication policy rather than offering it as an option. That is a natural-language policy concern because it forces a style choice on the user/agent interaction without opt-in or contextual justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest describes a behavioral skill for receiving and verifying code review feedback before implementation. Lines L203-L205 go beyond that guidance by prescribing use of a concrete GitHub API endpoint to post inline review replies, which introduces an operational integration capability not necessary to the stated purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.