Back to skill

Security audit

Blocknative

Security checks for vulnerabilities and agentic risk

Overview

The Blocknative lookups fit the stated purpose, but setup can execute unverified downloaded code without a clear user approval step.

Review the setup before enabling automatic use. Require approval before downloaded installer code runs, verify the CLI release, and decide whether its automatic agent-skill synchronization is acceptable. The complete bundled artifact was inspected, but the remote installers remain unverified; no malicious behavior 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 command installs or executes third-party software rather than searching or reading Blocknative data. Nothing in the supplied chunk establishes this installer as a supporting dependency for Blocknative functionality. The downloaded script's contents and subsequent effects are not visible.

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 fetched, unpinned script directly into Bash without integrity verification or an opportunity to inspect it; the PowerShell alternative has the same weakness. If the distribution endpoint or its delivery pipeline is compromised, attacker-controlled code would execute with the invoking user's permissions, potentially exposing local files and credentials.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to install software without explicitly obtaining approval or explaining that downloaded code will execute and may modify the local system. Although conditional on a missing dependency, this crosses from a read-only data task into local code execution without a clear authorization boundary.

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 79)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