Back to skill

Security audit

CurrencyBeacon

Security checks for vulnerabilities and agentic risk

Overview

The currency lookups are appropriately scoped, but setup can execute an unverified remote installer and introduce persistent changes to other agent skills without clear user control.

Review and install oo yourself before enabling this skill, and require approval before the agent runs either installer. Consider whether you accept OOMOL handling the connection and the CLI modifying other agent skills. Upstream documents OO_SKILLS_SYNC_DISABLED as a way to disable startup skill synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The bundled instructions were fully inspected; the remote installers and hosted implementation remain unverified. No artifact-backed malicious intent was found.

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 invokes a remote installer rather than searching or reading CurrencyBeacon data. Nothing in the chunk establishes this installer as a supporting dependency for the declared purpose. The downloaded script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied code performs only authentication, not CurrencyBeacon searching or reading. Authentication can be a supporting implementation detail, but this chunk provides no evidence connecting the login to CurrencyBeacon or implementing the declared data-access purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a remotely retrieved, mutable script directly into Bash without an independent integrity check or review; the PowerShell alternative uses the same download-and-execute pattern. Although installation serves a legitimate dependency need, compromise of the distribution endpoint could execute attacker-controlled code with the agent process's local permissions.

Content

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

Fallback setup executes remote installation scripts without warning the user about system changes or obtaining approval.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

A missing CLI triggers instructions to install software without first explaining the system changes or obtaining approval, expanding a data-reading request into local code execution. The missing-command prerequisite limits exposure, and enforced Bash(oo *) permissions could block these installer commands, but neither constitutes user consent to installation.

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