Back to skill

Security audit

Crossref

Security checks for vulnerabilities and agentic risk

Overview

The Crossref workflow is coherent, but setup can execute unverified downloaded code without clear user approval.

Review setup before installing. Use a reviewed, pinned CLI and require approval for installation changes. Check its automatic skill synchronization settings. Queries and references go through OOMOL and may incur charges. Installer contents and hosted connector behavior were not verified; 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
99% confidence
Finding

The supplied command does not query Crossref or read its data. It executes an external installer from cli.oomol.com, an undeclared capability with no demonstrated connection to the stated Crossref purpose. The mismatch is based on this visible behavior, not assumptions about what the remote script contains.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs login rather than the declared Crossref data operations. Nothing in the code establishes that this authentication is a supporting step for Crossref access.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a downloaded installer directly into bash executes mutable remote content with the agent process's privileges, without an independent integrity check or review. Compromise of the distribution endpoint could therefore enable arbitrary code execution, credential theft, or local data modification; the Windows installer uses an equivalent download-and-execute pattern.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

The setup workflow instructs the agent to execute remote installation scripts without warning the user about system changes or obtaining approval.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

A missing CLI causes the instructions to escalate a read-only research task into software installation without requiring informed user approval. The conditional setup limits when this occurs, but does not authorize changes to the user's environment or explain that downloaded code will execute.

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 86)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