Back to skill

Security audit

lfg-alarm

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the scans found one low-probability alert about an external service address, which reviewers judged consistent with the skill’s purpose.

The verdict is benign, not risk-free. The skill’s reported setup involves connecting to an external service and may involve signing in or using a personal key; consider whether you trust that service and are comfortable connecting your account before installing.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
2. Add the remote MCP server `https://mcp.lfg.gm` (Streamable HTTP, OAuth). The person signs in on lfg.gm with their LFG account and clicks **Allow**. If your client cannot do the sign-in, the person makes a personal key in the app (**Settings** > **AI apps and keys**; it starts with `lfg_pat_`) and you send it as `Authorization: Bearer <key>`.
3. Step-by-step setup for each AI app: https://lfg.gm/agents

Writing code instead? The SDK (`npm install lfg-alarm` or `pip install lfg-alarm`, with Vercel AI SDK tools and a LangChain toolkit, `langchain-lfg`) does the same: https://lfg.gm/developers. To ring a phone from a script with no key, POST to an Anything alarm's link: `curl -X POST https://api.lfg.gm/horn/<token>`. There is no LFG command-line tool.

If the tools are not connected, tell the person how to connect them (link https://lfg.gm/agents) instead of pretending to set an alarm, or that they can set it themselves in the app or at lfg.gm.