ClawHub
Back to skill

Security audit

Manual QA

Security checks for vulnerabilities and agentic risk

Overview

This skill gives QA checklist guidance for code changes and does not add hidden installation, persistence, or unrelated access.

Before installing, be aware that this skill may inspect local git diffs or PR diffs when you ask for QA or test planning. That is expected for its purpose, and it should ask before running agent-testable commands.

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
90% confidence
Finding

The skill description includes broad trigger phrases like "QA this," "test plan," and "what should I test," which can overlap with common review or analysis requests and cause the skill to activate in situations the user did not specifically intend. This increases the chance of misrouting user requests, potentially leading the agent to inspect diffs, PRs, or repository state unnecessarily and act on code-related context beyond the user’s precise ask.

Content

No source excerpt is available for this finding.