Back to skill

Security audit

Táve

Security checks for vulnerabilities and agentic risk

Overview

The Táve features fit their purpose, but setup executes unchecked downloaded software and leaves potential changes to other agent skills undisclosed.

Review setup before enabling this skill. Install a verified CLI release deliberately, use a Táve connection with only necessary access, and require approval before downloaded installers run. Consider disabling startup skill synchronization using OO_SKILLS_SYNC_DISABLED=1, as described in the linked CLI documentation. The installer payload and hosted connector were not verified; the artifact itself shows no malicious intent.

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
97% confidence
Finding

The supplied code performs remote software installation rather than searching or reading Táve data. Dependency installation can be a supporting implementation detail, but the supplied chunk establishes no relationship between this installer and the declared Táve functionality. The downloaded script's additional behavior cannot be determined from the provided code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into bash executes mutable remote code without a pinned version or independent integrity verification. A compromised distribution endpoint could execute code with the user's permissions, exposing local files and credentials; the legitimate OOMOL dependency and missing-CLI condition limit exposure but do not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes remote installation scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The missing-CLI fallback directs an agent to execute downloaded shell or PowerShell code without first explaining the local changes or obtaining installation approval. Although dependency setup is legitimate and conditional, it crosses from reading Táve data into arbitrary local execution with the invoking user's permissions.

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 78)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