ClawHub
Back to skill

Security audit

quality-gate

Security checks for vulnerabilities and agentic risk

Overview

The skill’s quality-gate purpose is coherent, but its broad triggers can reach workflows that commit code or post GitHub PR reviews.

Install only if you want an egregore-specific quality gate that may modify branches and post PR reviews through GitHub CLI. Prefer explicit invocation, verify the target branch and PR number, and consider adding a confirmation step before commits or GitHub review submission.

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)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

Using "review" as a trigger conflicts with a common built-in command name and creates a shadowing risk where this skill may be invoked instead of, or alongside, an expected native review function. In this skill's context, that is more dangerous because the workflow can fetch diffs, invoke other skills, and post GitHub reviews, so a mistaken activation can lead to unintended external actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad terms like "quality", "review", and the phrase "running quality checks before a PR", which can cause the skill to activate in contexts beyond the intended egregore pipeline. Because this skill orchestrates git, GitHub CLI, and other mapped skills, unintended activation could launch workflows or influence review actions when a user meant something more generic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.