Back to skill

Security audit

Merriam-Webster Collegiate

Security checks for vulnerabilities and agentic risk

Overview

The dictionary lookup is clearly scoped, but its setup can run an unchecked downloaded installer and introduce broader agent changes without clear user approval.

Review and install the CLI separately before allowing this skill to run. Check its automatic skill synchronization and disable it if unwanted, and confirm OOMOL account permissions and charges. The lookup and login instructions fit the purpose; the Review verdict concerns insufficient control over setup changes. The downloaded installers' exact behavior remains 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 remote script execution, not dictionary searching or reading. Nothing in the supplied code establishes the Oomol installer as a necessary supporting implementation detail for Merriam-Webster access. The contents and further effects of the downloaded script are not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code only invokes a login command; it does not search or read dictionary data. Authentication could be a supporting implementation detail if tied to the declared service, but the supplied content establishes no such relationship.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into Bash executes mutable remote code without a pinned version, integrity verification, or review. If the distribution endpoint or release pipeline is compromised, the installer could access or modify anything available to the invoking account; HTTPS does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Fallback setup executes remote installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

A missing CLI triggers instructions to execute a remote installer without first explaining local changes or obtaining explicit approval. This expands a dictionary lookup into local software installation and code execution; the fallback condition limits frequency but does not authorize the additional effects.

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 76)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