ClawHub
Back to skill

Security audit

self-reflection

Security checks for vulnerabilities and agentic risk

Overview

This is a fact-checking workflow skill that is coherent with its purpose, with some scope and resource-use caveats but no hidden or destructive behavior found.

Install this if you want an agent workflow for rigorous fact-checking. Be aware it may use multiple subagents and external source-fetching tools, so invoke it for answers that genuinely need verification rather than routine editing or low-stakes responses.

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
91% confidence
Finding

The activation description is overly broad: 'Use when you need to determine the accuracy of the answer' can match many normal requests for checking, revising, or validating output. That can cause the skill to trigger in routine situations without clear scope limits, leading to unnecessary autonomous verification steps, extra tool/subagent usage, and expanded exposure to untrusted external content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.