ClawHub
Back to skill

Security audit

Code Review

Security checks for vulnerabilities and agentic risk

Overview

This PR review skill is mostly coherent, but it can automatically post GitHub PR comments after broad review-style triggers without an explicit confirmation step.

Install only if you are comfortable with the skill reading GitHub PR and issue context and posting a team-visible PR comment. Prefer using it only when you explicitly want a review comment posted, and consider adding a confirmation step before `gh pr comment`.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation text is broad enough to match generic requests like 'code review' or reaching a workflow 'code review phase,' which can cause the skill to run in situations where the user did not specifically ask for this PR-review workflow. Because the skill has side effects later in execution, over-broad triggering increases the chance of unintended GitHub access and automated commenting.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill posts a PR comment via gh pr comment, but the user-facing description does not clearly disclose that execution will write to GitHub. Hidden write actions are dangerous because a user may invoke what sounds like an analysis-only review and unintentionally cause external side effects, including public or team-visible comments on the wrong PR.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.