Back to skill

Security audit

Prometheus Fire — 普罗米修斯之火

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: they report no AIG findings, while the main noted risk is an unpinned installation command.

The verdict is benign, but it does not mean risk-free. Before installing, consider that the manual command may download an unpinned CLI; verify the package and release before running it. The scan is partial: four referenced local files were not found, so the evidence does not cover them.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

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.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The installation example pins prometheus-fire@3.1.4 but leaves the executable npm package clawhub unpinned. Running this command can download and execute an unexpected or compromised CLI release with the user's terminal permissions; this is a supply-chain exposure, not an MCP server reference. Its placement as a manually executed installation example reduces automatic exposure but does not eliminate the risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.