ClawHub
Back to skill

Security audit

Truth first

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple evidence-checking workflow that tells the agent to verify claims with local evidence before answering.

Install this if you want stricter evidence-based answers. Be aware that using it may cause the agent to inspect local configs, logs, or environment files when verifying claims, so keep verification requests focused and review any proposed commands before running sensitive checks.

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
94% confidence
Finding

The README states the skill is 'automatically triggered for verification tasks' without defining clear scope boundaries, guard conditions, or examples of non-applicable cases. In an agentic system, an overly broad auto-trigger can cause the skill to activate on many prompts, potentially altering behavior unexpectedly, increasing tool use, and expanding the chance that adversarial or ambiguous inputs are treated as verification workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.