Back to skill

Security audit

eSignatures.com

Security checks for vulnerabilities and agentic risk

Overview

The contract workflow has sensible safeguards, but setup can execute unverified remote software without a clear approval step.

Review the setup behavior before installing. Prefer a separately reviewed, fixed CLI release and require approval before running downloaded installers. The CLI documents an OO_SKILLS_SYNC_DISABLED control for preventing automatic skill writes in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). OOMOL will mediate access to contract data and credentials. Only the Markdown skill was bundled; the live installer contents could not be verified.

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
98% confidence
Finding

The command executes an external installation script from cli.oomol.com, with no demonstrated connection to eSignatures.com. Although dependency installation can be a supporting implementation detail, this chunk provides no evidence that the CLI supports the declared purpose. The remote script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a live HTTPS download directly into bash executes remotely supplied code without pinning a version or independently verifying the artifact; the PowerShell alternative has the same issue. Compromise of the installation endpoint or its delivery infrastructure could execute attacker-controlled commands with the invoking user's permissions, potentially exposing local files and credentials. The domain is relevant to the documented tool, but that does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback workflow directs installation of downloaded executable code without explicitly requiring user approval for local software installation or explaining its system effects. Although conditional and relevant to the task, this can expand a service-data request into local code execution and environment changes that the user did not authorize.

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 83)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