ClawHub
Back to skill

Security audit

AI Receptionist: AI Phone Receptionist (OsmO)

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported external service connection appears consistent with the skill’s stated receptionist purpose, though the scan is incomplete.

The scanner verdict is benign, but confidence is medium and coverage is incomplete: Skillspector partially inspected the only component, reporting a malformed or unsupported manifest, and AIG reported no findings. Before installing, consider that the skill connects to a hosted service and review its OAuth sign-in and service terms, especially if calls or booking details may be involved.

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
  • 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 (6)

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 14)May include surrounding context.

md
spam, takes the message or booking request, follows the user's rules, and sends a summary. This skill
lets the user run that receptionist from their AI app through the hosted OsmO MCP server.

- MCP server: `https://api.getosmo.app/mcp` (Streamable HTTP, OAuth 2.1; no API key)
- Setup: install the OsmO app (https://getosmo.app/app), choose a plan, and turn on call forwarding
  on the user's number. The receptionist only answers calls once forwarding is on.
- To place outgoing calls instead, use the `osmo-phone-calls` skill.

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.

Claude Code

sh
claude mcp add --transport http osmo https://api.getosmo.app/mcp

then type /mcp inside Claude Code and sign in.

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 36)May include surrounding context.

Codex

sh
codex mcp add osmo --url https://api.getosmo.app/mcp
codex mcp login osmo

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 43)May include surrounding context.

OpenClaw

sh
openclaw mcp set osmo '{"url":"https://api.getosmo.app/mcp","transport":"streamable-http","auth":"oauth"}'
openclaw mcp login osmo

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 52)May include surrounding context.

yaml
mcp_servers:
  osmo:
    url: "https://api.getosmo.app/mcp"
    auth: oauth

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 56)May include surrounding context.

auth: oauth

text

Sign-in opens `https://api.getosmo.app/mcp/oauth/connect` in the browser. The user enters their
phone number and a one-time code there. Never ask for that code in chat, and never store or
repeat it.