ClawHub
Back to skill

Security audit

GitHub AI Daily Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily AI digest workflow that searches public sources and writes the resulting report to user-specified Feishu destinations.

Before installing, make sure the Feishu open_id and document tokens point only to destinations where you want automated report content written. Use the optional backlog token only if you want the skill to add project-tracking items outside the main daily archive.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Low
Confidence
87% confidence
Finding
The manifest description says the skill fetches content, sends a Feishu report, and prepends it to a Feishu document as a daily digest archive. SKILL.md also introduces a separate optional capability to append projects into a backlog/TODO document, which is a distinct project-tracking workflow not mentioned in the manifest description.

Static analysis

No suspicious patterns detected.