Back to skill

Security audit

folk

Security checks for vulnerabilities and agentic risk

Overview

The skill requires approval for folk changes, but its setup can execute unverified code and its CLI can install additional agent skills without explaining that here.

Review and install a fixed CLI version yourself before use, and connect only the intended folk account. Current upstream supports OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; verify that control for your chosen release in the [CLI documentation](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Keep the required confirmations for record changes. The external installer payload and exact installed release remain unverified.

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
95% confidence
Finding

The supplied code performs remote installer execution rather than folk.app data management. Although installing a dependency can be a supporting implementation detail, this chunk establishes no connection between the Oomol installer and the declared folk functionality. The downloaded script's contents and any 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 instructions pipe a remotely retrieved, unpinned script directly into Bash without integrity verification or review; the PowerShell alternative uses the same download-and-execute pattern. If the distribution endpoint or its delivery infrastructure is compromised, the script could execute arbitrary commands with the invoking user's permissions. The missing-CLI prerequisite limits exposure to setup, but does not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 69)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 90)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