Back to skill

Security audit

Baidu Maps

Security checks for vulnerabilities and agentic risk

Overview

The map features match the description, but automatic setup executes unverified downloaded code and may install additional agent skills.

Review and install a verified, pinned CLI release before use, and check which additional agent skills it installs or updates. Map queries send their location inputs through OOMOL to Baidu Maps, so submit only information you intend to share. The bundled instructions were fully inspected; remote installer contents and hosted-service behavior remain outside that inspection.

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
97% confidence
Finding

The supplied chunk performs remote script execution and contains no Baidu Maps search or data-reading behavior. Dependency installation could be a supporting implementation detail, but the supplied content establishes no such relationship. The downloaded script's contents and subsequent effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied code performs a login operation rather than searching or reading Baidu Maps data. Authentication can be a supporting implementation detail, but this chunk provides no evidence that the oo login supports Baidu Maps or accesses its services.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command immediately executes whatever script the installation endpoint returns, without pinning or verifying its contents. HTTPS protects transport but does not protect against a compromised publisher or distribution infrastructure; this is the same underlying installation vulnerability identified in the setup-workflow finding, not an additional independent exploit.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

The workflow sends potentially sensitive location data to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow instructs the agent to send action payloads through OOMOL to Baidu Maps; these payloads can contain addresses, coordinates, IP addresses, or route endpoints. Although the providers are identified, the skill does not warn about disclosing sensitive location information and instead labels all read actions safe to run directly.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The setup instructions pipe remotely retrieved content directly into Bash or PowerShell without an integrity check, review step, or explicit approval for executing installation code. A compromised distribution endpoint or modified installer could execute arbitrary commands with the invoking user's permissions; the missing-CLI condition limits exposure but does not make the downloaded code trustworthy.

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 89)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