ClawHub
Back to skill

Security audit

Merge Check

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently gathers read-only GitHub pull request data to estimate merge likelihood, with no hidden persistence or destructive behavior found.

Before installing, understand that this skill will use your configured GitHub CLI access to read PR metadata, review comments, checks, files, and recent author history for the PR you provide. Use it only for repositories and pull requests whose discussion and metadata you are comfortable having analyzed for merge-likelihood signals.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is broad enough to match common user requests like reviewing a PR or assessing PR quality, which can cause the agent to invoke this skill in situations beyond narrow mergeability prediction. That increases the chance of over-triggering on general code review tasks, potentially displacing more appropriate skills and exposing repository metadata, review history, and social signals when the user did not explicitly ask for merge-likelihood analysis.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
This markdown file includes natural-language guidance that can penalize contributors based on language proficiency. Under the policy, language or locale constraints should not be imposed without explicit user opt-in or clear justification.

Static analysis

No suspicious patterns detected.