Back to skill

Security audit

Google Forms

Security checks for vulnerabilities and agentic risk

Overview

The Google Forms workflow has clear safeguards, but setup can execute unverified software whose documented behavior includes installing additional persistent agent skills.

Review and approve the CLI installation separately. Consider disabling automatic skill synchronization before running it; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. Connect only the Google Forms permissions you need and retain confirmation for changes. Installer contents and hosted connector behavior 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
  • 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
93% confidence
Finding

The supplied chunk performs remote script execution rather than any visible Google Forms operation. Installation can be a supporting implementation detail, but this chunk establishes no relationship between the Oomol installer and the declared Google Forms functionality. The remote script's contents and any further effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a mutable remote installer directly into bash gives the fetched content code-execution privileges without an integrity check or review opportunity. HTTPS protects transport but does not protect against a compromised distribution server or malicious installer update; this is the same underlying installation risk identified by SQP-2, not an independent exploit.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup workflow instructs execution of remotely downloaded installer scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The setup workflow instructs immediate execution of remotely retrieved shell and PowerShell scripts without verifying their contents or obtaining explicit approval for local software installation. Setup is conditional on a missing CLI, which limits exposure, but a compromised installer source could still execute arbitrary code with the invoking user's privileges.

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 82)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