ClawHub
Back to skill

Security audit

Daily Digest

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives instructions for a read-only Gitee daily digest, with no code execution, persistence, or data mutation.

Install this only if you want the agent to read your Gitee notifications, user identity, PRs, and issues to summarize your work. For ambiguous requests like daily summary, confirm that you want a Gitee-based digest before letting it fetch account or repository data.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description includes broad trigger phrases such as "daily summary," "what's on my plate today," and "show my notifications," which can match common user requests and cause the skill to activate in situations where the user did not specifically intend Gitee data access. Because the skill aggregates account notifications, PRs, and issues, over-broad routing increases the chance of unexpected access to privacy-sensitive workspace data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to aggregate unread notifications, pending PRs, open issues, and current user information, but it provides no explicit user-facing warning or consent check that privacy-sensitive account and repository data will be accessed. In an ambiguous invocation, this can lead to unexpected disclosure of work activity, assignments, and cross-repository notifications that the user may not have intended to surface.

Static analysis

No suspicious patterns detected.