Back to skill

Security audit

APIVerve

Security checks for vulnerabilities and agentic risk

Overview

The APIVerve workflow fits its purpose, but setup can execute an unverified installer and introduce broader agent changes without clear user control.

Review the setup behavior before installing. Prefer a separately reviewed, verified CLI release, and inspect or disable its automatic skill synchronization. Installer contents and the exact installed release remain unverified. Submit only information you intend to share with OOMOL and APIVerve.

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 does not search or read APIVerve data. It fetches and executes an installer from a different service, introducing an undeclared installation and arbitrary remote-code execution capability. The downloaded script is not supplied, so its further effects cannot be determined.

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 verifying a pinned artifact or reviewing it first. Compromise of the distribution endpoint could therefore yield arbitrary code execution with the agent process's permissions; this is the same underlying installer issue identified above, not an independent attack path.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

The action workflow sends user-provided payloads to external services without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The workflow instructs the agent to submit JSON payloads through the OOMOL connector to APIVerve, but does not warn that user data is transmitted to these external services. Inputs can include personal information such as the date of birth used by calculate_age; describing untagged actions as safe reads does not address that disclosure.

Content

No source excerpt is available for this finding.

First-time setup executes downloaded installation scripts without warning about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs execution of downloaded shell or PowerShell code without an explicit approval gate or explanation of resulting system changes. Although conditional and relevant to setup, this expands a data-access request into host software installation, potentially exposing the executing user's files and credentials if the installer is compromised.

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 84)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