ClawHub
Back to skill

Security audit

esa

Security checks for vulnerabilities and agentic risk

Overview

The esa workflow requires approval for changes, but its required CLI can also install other agent skills without that broader behavior being disclosed here.

Review the CLI's broader skill-installation behavior before installing. Use a verified CLI release and configure OO_SKILLS_SYNC_DISABLED=1 for subsequent invocations if you want to prevent startup skill synchronization, as documented in the [environment controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Esa requests pass through OOMOL. Actual installer contents and hosted execution were not verified.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code performs remote software installation rather than esa.io data operations. Installation can be a supporting implementation detail, but this chunk provides no evidence that the Oomol installer supports the declared esa functionality. The downloaded script's contents and 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

The setup command pipes a remotely fetched, unpinned script directly into Bash without independent integrity verification or review; the PowerShell alternative has the same weakness. Compromise of the installer host or distribution pipeline could execute arbitrary code with the invoking user's permissions and expose local credentials or files. Its legitimate dependency-installation purpose and missing-CLI trigger reduce routine exposure but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

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 105)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