Back to skill

Security audit

PubMed

Security checks for vulnerabilities and agentic risk

Overview

This PubMed skill needs review because its setup directs the agent to run unverified downloaded software without a separate approval step.

Verify and install the OOMOL CLI yourself before enabling this skill, and prevent automatic execution of its installer fallback. Review the CLI's installation of additional agent skills and understand that PubMed requests pass through OOMOL and may use credits. The PubMed workflow shows no malicious intent, but the remote installer and its full effects remain unverified.

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 performs a login operation and contains no PubMed search or reading functionality. Nothing in the supplied code connects this authentication step to PubMed, so it is not established as a supporting implementation detail of the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command does not access PubMed or implement PubMed search or reading. It executes an external installation script from cli.oomol.com, with no demonstrated connection to the declared PubMed functionality. The remote script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a mutable HTTPS response directly into bash executes whatever the installer endpoint supplies, without pinning or verifying the artifact. Compromise of the distribution endpoint could therefore compromise the local agent environment; HTTPS protects transport but does not establish that the delivered script is trustworthy.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Fallback setup executes remotely downloaded installer scripts without warning about system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without an explicit approval step or integrity verification. Although it runs only when the CLI is missing, a compromised installer source could execute arbitrary code with the agent process's privileges; this is unnecessary exposure for a read-only PubMed task.

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 83)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