ClawHub
Back to skill

Security audit

Prometheus Fire — 普罗米修斯之火

Security checks for vulnerabilities and agentic risk

Overview

This is a conversational self-reflection skill with no declared tool access, and its privacy cautions are clearly disclosed.

Before installing, confirm the ClawHub page and author are the expected gechengling/prometheus-fire source. When using it, avoid entering identifiers, credentials, client lists, or confidential business details because your prompts are still processed and retained according to the AI platform's policies.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The README includes a shell command using npx clawhub install prometheus-fire@3.1.4 without pinning the clawhub package itself. Even though the skill says the command is only reference text and stresses version-pinning for the skill slug, npx clawhub still fetches the latest CLI/package version at execution time, creating a supply-chain risk if that upstream package is compromised or changed unexpectedly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.