Back to skill

Security audit

U301

Security checks for vulnerabilities and agentic risk

Overview

The U301 actions have approval safeguards, but setup executes unverified downloads and the required CLI can persistently install other agent skills without disclosure here.

Review the setup before installing. Use a verified CLI release and set OO_SKILLS_SYNC_DISABLED=1 before invoking it if you do not want automatic changes to other agent skills; this control is documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Connecting U301 authorizes OOMOL-mediated account operations. Keep the explicit approvals for creating and deleting links. The remote installers and exact deployed connector implementation were not 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
  • 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 command executes an Oomol-hosted installer rather than performing U301 data operations. Although dependency installation can be a supporting implementation detail, the provided chunk establishes no relationship between this installer and U301. The downloaded script's contents and further 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 setup command pipes a remotely fetched, unpinned script directly into Bash, allowing its contents to execute with the agent process's permissions without prior inspection or independent integrity verification. A compromised distribution endpoint could therefore execute arbitrary code and access local data; the adjacent PowerShell command has the same weakness. The missing-CLI condition and legitimate dependency reduce exposure but do not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 57)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 78)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