ClawHub
Back to skill

Security audit

EasyPost

Security checks for vulnerabilities and agentic risk

Overview

The EasyPost workflow has sensible controls, but setup can execute unchecked downloads and introduce broader agent changes without clear approval.

Review setup before installing. Use a reviewed CLI distribution, require approval for local installation, and decide whether to disable automatic skill synchronization. Connecting EasyPost also entrusts OOMOL with service credentials and shipping information. The bundled instructions show no malicious behavior, but the remote installer remains unverified.

A.I.G

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

SkillSpector

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
96% confidence
Finding

The supplied command contains no EasyPost interaction and instead executes an external installer. Nothing provided establishes this installation as a supporting dependency for the declared EasyPost functionality. The remote script's subsequent behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes whatever the installation endpoint serves without independently verifying its integrity or reviewing it first. Compromise of the endpoint or its delivery pipeline could result in arbitrary code execution with access to local files and credentials; the conditional setup context reduces exposure but does not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to execute remotely downloaded installation scripts without explaining their execution privileges or requiring explicit installation approval. Although conditional and relevant to setup, this crosses from an EasyPost request into local software installation and could expose the agent's environment to arbitrary code.

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 81)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