Back to skill

Security audit

AMap

Security checks for vulnerabilities and agentic risk

Overview

The AMap features fit the stated purpose, but automatic setup runs unchecked downloaded software and leaves broader changes to agent skills unexplained.

Review the CLI installation separately before allowing automatic setup, preferably using a verified release. The current CLI documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup writes to agent skill directories; configure it before running oo if those changes are unwanted. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables) Mapping requests send their supplied location or IP information through OOMOL to AMap. The external installer and downloaded release remain unverified; no malicious behavior was established.

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
96% confidence
Finding

The supplied command executes an external installation script, while the description only declares AMap searching and reading. Nothing in the supplied chunk establishes that this installer is a supporting dependency for AMap access. The remote script's contents are not provided, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk only invokes login; it contains no AMap search or data-reading behavior. Authentication could support an AMap integration, but the supplied code establishes no such relationship, so its demonstrated purpose differs materially from the description.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a remotely fetched, unpinned script directly into Bash without integrity verification or review; the PowerShell fallback uses the equivalent download-and-execute pattern. If the distribution endpoint or release pipeline is compromised, attacker-controlled code executes with the agent process's permissions and could access local data or credentials; restricting installation to a missing-CLI error reduces exposure but does not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

The action workflow lacks a privacy warning for location and IP data sent to external services.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to submit action payloads through OOMOL to AMap, which can include user addresses, coordinates, IP addresses, or route endpoints. Although the connector relationship is disclosed, there is no warning about transmitting potentially sensitive location data, and line 58 characterizes read actions as safe to run directly without distinguishing privacy effects from state changes.

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 90)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