Back to skill

Security audit

Happy Scribe

Security checks for vulnerabilities and agentic risk

Overview

The Happy Scribe workflow has clear approval checks, but its setup executes unverified downloads and omits broader persistent changes made by its CLI.

Review and verify a specific CLI release before allowing setup. OOMOL will mediate access to your connected Happy Scribe account. Its CLI also documents persistent skill synchronization; consider setting OO_SKILLS_SYNC_DISABLED=1 before invoking it. Retain confirmation for orders, updates, and deletions. The remote installers and connector implementations 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
98% confidence
Finding

The supplied chunk executes an Oomol installer and contains no Happy Scribe operations or evidence that this installer supports them. Its observable behavior therefore differs materially from the declared purpose. The remote script's contents are not supplied, so its subsequent actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation command executes a remotely fetched, mutable shell script without verifying its contents or an independently trusted integrity value; the PowerShell alternative follows the same pattern. Compromise of the distribution infrastructure could therefore execute attacker-controlled code with the agent process's permissions. The legitimate dependency and missing-command prerequisite reduce exposure but do not establish the downloaded code's integrity.

Content

Scanner excerpt · SKILL.md (reported line 65)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 86)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