ClawHub
Back to skill

Security audit

Ai News Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a straightforward AI-news research task and saves a local markdown report, with no evidence of hidden execution, credential misuse, or unsafe persistence.

Before installing, note that the skill is designed to browse current AI news and save a dated Markdown report under ~/clawd/reports. Confirm the save location if you do not want files written there, and treat email delivery as opt-in only after you configure it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs the agent to write a report file to a local path without clearly disclosing that side effect to the user at run time or requiring confirmation. While saving a report is consistent with the skill's stated purpose, undisclosed filesystem writes can surprise users, create unwanted persistence, or overwrite expected data in the target directory.