Back to skill

Security audit

currencyapi

Security checks for vulnerabilities and agentic risk

Overview

The currency-data features fit their purpose, but setup can execute unverified remote installers and introduce broader agent changes without clear user approval.

Review the setup behavior before installing. Install a reviewed, integrity-verified CLI release separately and require approval for local changes. Review or disable its automatic skill synchronization, and connect only the intended currencyapi account. The remote installer contents and hosted credential handling remain unverified; the artifacts do not establish malicious intent.

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 missing-CLI fallback expands a read-oriented task into executing remote installation code locally without an explicit approval or integrity-verification step. OOMOL is actually disclosed as the integration provider, so this is not evidence of a concealed third party or malicious purpose; the vulnerability is the unsafe installation workflow, overlapping with SQP-2 and SC2.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied chunk performs only a login operation; it does not search or read currencyapi data. Authentication could support an API integration, but nothing in this chunk establishes that this login is for currencyapi or supports the declared functionality.

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 content without a pinned version, integrity verification, or review. If the installer hosting or distribution pipeline is compromised, the command can run attacker-controlled code with the invoking user's privileges; the legitimate provider domain and conditional setup context do not eliminate this supply-chain risk.

Content

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

The setup workflow executes remotely downloaded installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions direct execution of downloaded shell and PowerShell scripts without first describing local changes or obtaining explicit installation approval. Restricting this behavior to a missing dependency reduces exposure, but a currency-data request still does not inherently authorize running an installer with the user's local privileges.

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