Back to skill

Security audit

ArcGIS Online

Security checks for vulnerabilities and agentic risk

Overview

The ArcGIS functions fit the stated purpose, but missing-software recovery tells the agent to run unverified online installers without a clear approval step.

Review and install the CLI separately before enabling the skill, and require approval for installation changes. ArcGIS requests use your OOMOL-connected account and may incur charges. The complete bundled skill was inspected; remote installers, CLI code, and hosted services were not verified. The concern is the uncontrolled setup path, not evidence of malicious intent.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code executes a remote installer and contains no ArcGIS Online search or data-reading operations. Nothing in the supplied content establishes that this installation is a supporting requirement for the declared functionality. The downloaded script's contents and effects cannot be determined from this command alone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into Bash executes mutable network content without a pinned version or independent integrity verification. Compromise of the distribution endpoint or release pipeline could yield arbitrary code execution under the invoking account; the PowerShell example has the same weakness. HTTPS and conditional execution reduce some exposure but do not establish script integrity.

Content

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

Fallback setup executes downloaded installer scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to install software after a missing-command error without first obtaining approval for local system changes. Although conditional and relevant to the task, installation executes code with the invoking user's privileges and goes beyond an ArcGIS read request; the declared tool restriction may limit execution but does not make these instructions safe.

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