ClawHub
Back to skill

Security audit

Moss Deep Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple deep web research prompt with no bundled code, persistence, credential access, or hidden behavior.

Install this if you want an agent to run more expansive web research and synthesize sources. Be aware that its trigger wording is broad, so it may use multi-round search for requests that could otherwise be answered with a lighter lookup.

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
93% confidence
Finding

The skill description advertises activation for broad requests like comprehensive analysis or detailed research, which overlap heavily with ordinary assistant behavior. This can cause unintended invocation of the skill, leading to unnecessary external searching, unexpected data flow to tools, or bypass of more narrowly scoped workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions in the workflow are underspecified, including generic cues like needing multi-source analysis or insufficient Brave results, which may apply to many normal tasks. In a tool-using skill, ambiguous triggers increase the chance of over-collection, unnecessary web access, and execution of a more powerful research flow than the user intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.