ClawHub
Back to skill

Security audit

bug-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward bug-review workflow; its main caveat is that its broad trigger words may cause it to activate in ordinary coding conversations.

Before installing, be aware that this skill may activate for general words like fixes or verification. Its instructions are otherwise typical for a bug-review assistant: it may inspect code, propose changes, and run project test or lint commands when the user directs that workflow.

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
Confidence
95% confidence
Finding
The trigger list includes broad, common terms like "bugs," "fixes," and "verification," which can cause the skill to activate in many ordinary development conversations beyond the author's intended scope. In an agent system, unintended invocation can lead to inappropriate workflow takeover, unnecessary tool use, or exposure of project context to a skill that was not deliberately selected.

Static analysis

No suspicious patterns detected.