ClawHub
Back to skill

Security audit

TrawlingWeb

Security checks for vulnerabilities and agentic risk

Overview

The search workflow is coherent, but missing-tool setup directs the agent to execute unverified downloaded code without clear user approval.

Review and install the CLI separately before allowing searches, including its documented management of other agent skills. Require approval before any downloaded installer runs. OOMOL mediates account access and search requests; the remote installer's exact changes could not be verified.

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
  • 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 fetches and executes an installer from cli.oomol.com. No TrawlingWeb access or data-reading behavior is shown, and no connection establishing this installer as a supporting dependency is provided. Remote installer execution is a materially different capability from the declared search-and-read purpose. The downloaded script's further actions cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk performs only an authentication command, not TrawlingWeb searching or reading. Authentication could be a supporting implementation detail if tied to TrawlingWeb, but the supplied content establishes no such connection.

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 verifying its contents, signature, or expected digest; the PowerShell alternative has the same execution pattern. If the distribution endpoint or delivery chain is compromised, attacker-controlled code could run with the agent process's permissions and access local files or credentials. The OOMOL domain is relevant to the dependency, but relevance and HTTPS do not establish script integrity.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

A missing CLI triggers instructions to execute a downloaded installer without first explaining the system changes or requiring explicit installation approval. Installing a dependency is legitimate here, but this fallback expands a read-oriented task into local code execution; the conditional trigger reduces exposure without establishing user consent.

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 76)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