Back to skill

Security audit

oya-browser

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports account creation using the user's email without a clear privacy warning; the scan also raised a possible cookie theft signature, though its review disagreed.

Review the account setup and cookie import steps before installing. Consider whether you are comfortable sharing an email with Oya to create an account and importing browser cookies, and whether you can approve those actions knowingly. The scan was partial because a referenced local path was missing, so its evidence does not establish that the skill is safe.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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 (2)

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

of your own (saved there). const { claimUrl } = await Oya.signup({ email: "<the user's email>" });

const oya = new Oya(); const browser = await oya.desktop.connect(); // the user's own browser, with their logins

text

`desktop.connect()` pairs the Oya desktop app when it is not connected yet: tell the user to click Connect in the Oya window and keep the login import ticked. The import copies the cookies of the user's usual browser into the Oya app on the same computer, so sites are already signed in; nothing is sent anywhere. On macOS the OS asks once before Oya may read Chrome's cookie store. If the app is missing, the error gives the download link. `claimUrl` matters only for Oya Cloud browsers: send it to the user then.

MCP tools, when the user already set them up, work too:
`claude mcp add --transport http oya https://oyabrowser.com/mcp/pool --header "Authorization: Bearer $OYA_API_KEY"`. The CLI is `npm install -g @oya-ai/cli`.

## Over MCP

1. `start_browser`, starts a browser

The SDK setup sends the user's email to Oya to create an account without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The setup instructs the agent to create an Oya account using the user's email without first obtaining approval for that disclosure and account creation. Although signup is relevant to this browser service, authorization to browse or configure automation does not necessarily authorize registering the user with a third party.

Content

No source excerpt is available for this finding.