ClawHub
Back to skill

Security audit

industry-report-digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a report-summarization template with no code, persistence, credential access, or hidden behavior.

Installers should understand this skill may trigger on broad report-summary wording, but its behavior is limited to structuring and summarizing supplied report content. It does not add code execution, persistence, credential use, or hidden data flows.

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 includes broad trigger phrases like 'report summary' and 'extract insights' that can match many ordinary summarization requests without clearly requiring an industry report or long-form analyst document. This can cause the agent to invoke a specialized workflow in unintended contexts, leading to scope hijacking, user confusion, and unreliable outputs based on the wrong task framing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'When to use' guidance uses ambiguous phrases such as '这份报告重点是什么' and '帮我拆一下' without enough boundary conditions, so the skill may activate for many generic 'summarize this' requests. In an agent setting, overly permissive activation expands the skill's authority beyond its intended niche and increases the chance of misrouting user inputs or applying report-specific assumptions to unrelated content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.