Back to skill

Security audit

Browserless

Security checks for vulnerabilities and agentic risk

Overview

The Browserless workflow is coherent, but its automatic software setup and undisclosed agent-skill changes need review.

Review and install the CLI yourself before enabling this skill. Consider disabling automatic skill synchronization with OO_SKILLS_SYNC_DISABLED=1, as documented by the publisher, and send only URLs and payloads you intend OOMOL and Browserless to process. All bundled artifact text was inspected, but the remote installers and exact CLI release were not verified.

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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote installer execution, not Browserless searching or data reading. Nothing in the supplied chunk establishes this installation as a supporting requirement for Browserless functionality. The downloaded script's further behavior is not visible.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied code only invokes a CLI login command. It neither performs Browserless operations nor establishes that this authentication is a supporting step for Browserless. Its observable purpose therefore differs materially from the declared search-and-read functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without pinning or verifying its contents. HTTPS protects transport but does not prevent malicious changes following compromise of the distribution source; execution could expose local credentials or modify files accessible to the process.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The action workflow sends request payloads to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to submit action payloads through OOMOL to Browserless, but does not warn that submitted URLs and other request data are disclosed to those services. Identifying the connector and explaining server-side credential handling does not warn users about potentially sensitive information in the payload.

Content

No source excerpt is available for this finding.

The setup workflow executes downloaded installer scripts without warning about their system impact.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

On a missing-CLI error, the setup instructions direct execution of remotely downloaded shell or PowerShell code without an explicit installation approval or integrity-verification step. If followed with sufficient tool permissions, a compromised installer source could execute arbitrary code with the agent process's privileges; this overlaps with the SC2 finding rather than constituting a separate exploit.

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 78)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