ClawHub
Back to skill

Security audit

OpusFlame Deep Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed deep-research workflow that uses multiple model agents, web research, saved reports, and PDF delivery in ways that fit its stated purpose.

Before installing, understand that deep research requests will be sent through several model agents and web tools, and the generated research will be saved locally and packaged as a PDF for delivery. Avoid using it for confidential or regulated information unless those storage and provider-sharing behaviors are acceptable.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to save multiple reports to persistent storage, generate a PDF in an outbound directory, and send that file to the user, but it does not require explicit user consent or a warning before performing those side effects. In an autonomous multi-agent workflow, this increases the risk of unintended data retention, creation of sensitive artifacts, and accidental exfiltration of research outputs or embedded sensitive content.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The instruction hard-codes a Chinese-language filename suffix for the final report regardless of user preference or locale. This is a natural-language locale choice imposed by the skill rather than an opt-in or documented region-specific requirement.

Static analysis

No suspicious patterns detected.