Back to skill

Security audit

Vectera

Security checks for vulnerabilities and agentic risk

Overview

The Vectera actions have clear safeguards, but setup can run unverified software and change other agents’ installed skills without clear approval.

Review local setup before proceeding. Install a reviewed CLI release yourself, consider disabling its automatic skill synchronization, and connect only the intended Vectera account. Keep the existing confirmation requirement for meeting-room and access changes. The remote installer’s exact behavior remains unverified; no malicious payload was established.

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
98% confidence
Finding

The supplied code runs an Oomol installer rather than performing any visible Vectera operation. Although installation can be a supporting implementation detail, nothing supplied establishes this installer as a dependency of the declared Vectera functionality. The downloaded script's contents and further effects are not shown.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS download directly into Bash executes whatever the installation endpoint returns with the invoking user's privileges, without a separate verification step. Compromise of the distribution endpoint could therefore enable local data theft or modification; the legitimate CLI dependency and missing-tool condition do not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about running remote code on the user's system.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions direct execution of downloaded shell and PowerShell scripts without explaining that they run remote code or requiring explicit installation approval. Restricting setup to a missing-CLI error reduces exposure, but a routine Vectera request can still lead to security-sensitive local changes without informed consent.

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 83)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