ClawHub
Back to skill

Security audit

工作日报

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps format user-provided work updates into a daily report and does not request tool, file, network, credential, or persistence access.

This is suitable to install if you want help drafting Chinese work daily reports. Review generated reports for workplace sensitivity and accuracy before sending, and invoke it explicitly when you want日报-style formatting.

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
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description uses broad natural-language triggers around common workplace actions like writing a daily report or summarizing progress for a leader. This can cause the skill to activate in loosely related conversations and process content the user did not intend to route through this skill, creating prompt-routing and context-misuse risk rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage examples are short, everyday phrases that overlap with normal project communication, such as organizing progress for leadership. Ambiguous examples increase the chance of accidental invocation in ordinary chat, which may lead to unwanted transformation of user content or interference with the intended assistant behavior.

Content

No source excerpt is available for this finding.