Back to skill

Security audit

WebScraping.AI

Security checks for vulnerabilities and agentic risk

Overview

The web-reading workflow fits its purpose, but fallback setup can execute an unverified remote installer without a separate user approval step.

Review and approve CLI installation separately, preferably using a verified fixed release. Check whether its bundled-skill synchronization is acceptable before first use. Requests use your connected OOMOL/WebScraping.AI account and may consume credits. The review concern is uncontrolled setup execution; the inspected artifact does not establish malicious intent, and the remote installers 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote installer execution, not WebScraping.AI searching or reading. No connection is shown that would establish this installation as a supporting implementation detail of the declared purpose. The downloaded script is not supplied, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs only a login operation and contains no WebScraping.AI search or reading behavior. Authentication could be a supporting implementation detail, but nothing in this chunk connects oo auth login to WebScraping.AI or its declared functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash pipeline executes the installation endpoint's current response without version pinning or independent integrity verification. Although the endpoint belongs to the documented connector platform and uses HTTPS, compromise of its hosting or release pipeline could execute attacker-controlled code with local access; the PowerShell alternative has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Automatic setup executes downloaded installer scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

When the CLI is missing, the skill directs installation by immediately executing downloaded shell or PowerShell code without an explicit approval checkpoint or warning about local changes. The failure-triggered condition limits exposure, but a routine prerequisite error can still lead to arbitrary code execution 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 80)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