Back to skill

Security audit

BrowserStack

Security checks for vulnerabilities and agentic risk

Overview

The BrowserStack workflow is clearly scoped, but setup directs the agent to execute downloaded software without requiring approval or verifying it first.

Review the setup before installing. Prefer a pinned, independently verified CLI installation and require approval before the agent installs software. Check which additional agent skills the CLI installs. OOMOL will mediate your connected BrowserStack access; the remote installer contents and full local effects remain unverified.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command accesses Oomol infrastructure and executes its installer rather than performing BrowserStack operations. Nothing in the supplied chunk establishes this installer as a supporting dependency for BrowserStack, so its behavior materially differs from the declared purpose. The downloaded script's further actions cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote code without a pinned version, independent integrity verification, or review. Compromise of the installer hosting or distribution pipeline could yield arbitrary code execution with the invoking user's permissions; the PowerShell fallback has the same issue, although execution is conditional on missing tooling.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Fallback setup executes a remotely downloaded installer without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback instructs the agent to install software after a missing-command error without requiring approval for local system changes. Although limited to first-time setup, a BrowserStack request does not itself authorize installing software or executing an installer with the agent's local permissions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources