Back to skill

Security audit

TinyFish

Security checks for vulnerabilities and agentic risk

Overview

TinyFish operations have clear approval checks, but setup executes an unverified online installer and leaves broader agent changes undisclosed.

Review and install a verified CLI release yourself before use. Its current upstream documentation provides OO_SKILLS_SYNC_DISABLED=1 to prevent startup writes to agent skill directories. Retain the skill's approval checks for browser actions, profile uploads, vault connections, monitors, and payments. The installer contents and exact release selected by the fallback 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
98% confidence
Finding

The supplied code installs software through an Oomol-hosted script rather than performing TinyFish data operations. Nothing in the provided material establishes this installation as a supporting dependency for TinyFish. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The installation command pipes mutable remote content directly into Bash without a pinned version, independent integrity verification, or a review step; the PowerShell alternative has the same weakness. If the distribution endpoint or release pipeline is compromised, running this fallback could execute attacker-controlled code with the agent process's permissions, potentially exposing local credentials and files. Its legitimate dependency-installation purpose and missing-CLI condition reduce exposure, but do not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 97)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 118)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