Back to skill

Security audit

OpenAlex

Security checks for vulnerabilities and agentic risk

Overview

The OpenAlex features fit the stated purpose, but setup can automatically run an unverified online installer without asking first.

Review setup before installing. Install a verified CLI release yourself, approve its local changes, and check whether automatic synchronization of other agent skills is enabled. OpenAlex requests use your OOMOL-connected account. The bundled skill was fully inspected, but the external installers and hosted connector implementation were not verified; no malicious intent 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk performs remote software installation, not OpenAlex data access. No connection between the Oomol installer and the declared OpenAlex functionality is established, so this is not supported as a mere implementation detail. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS response directly into Bash executes mutable remote code without artifact verification or review before execution. HTTPS protects transport but not against a compromised vendor endpoint or release process; this is the same underlying installation risk as SQP-2, not an independent exploit.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Fallback setup executes remote installation scripts without warning about their system access.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback directs the agent to execute a remotely fetched installer without requiring informed approval or verifying the downloaded artifact. Although dependency setup is legitimate and conditional here, a compromised installer could execute with the invoking account's permissions, accessing local files or credentials; the PowerShell example has the same risk.

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 80)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