Back to skill

Security audit

Tavily

Security checks for vulnerabilities and agentic risk

Overview

The Tavily workflow is coherent, but its required CLI can persistently change other agents’ installed skills without this skill explaining that behavior.

Review the CLI’s installation and skill-sync behavior before using this integration. Prefer a verified, pinned installation and disable startup skill synchronization before the first invocation if you want to avoid changes to other agents; the publisher documents OO_SKILLS_SYNC_DISABLED=1 in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). OOMOL mediates requests and provider credentials. No malicious intent was established, but the remote installers and downloaded executable 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose concerns Tavily, but the code executes an installer hosted on an Oomol domain without showing any connection to Tavily. This is a materially different action, not an established supporting implementation detail. The remote script's contents and further effects cannot be determined from the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied code performs a CLI login rather than the declared Tavily operations. Authentication could be a supporting implementation detail, but the chunk provides no evidence that oo auth login authenticates to Tavily or supports the described functionality. The mismatch assessment is limited to the supplied code; the login destination and credential handling are not established.

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, mutable script directly into Bash without pinning or integrity verification; the PowerShell alternative follows the same download-and-execute pattern. Compromise of the distribution endpoint could execute arbitrary code with the invoking user's privileges, potentially exposing local credentials and files. Restricting this behavior to missing-CLI setup reduces exposure but does not establish the downloaded code's integrity.

Content

Scanner excerpt · SKILL.md (reported line 61)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 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