Pendo

• Outcome: Review
• Latest audit: Nov 3, 2026 · 10:51 AM UTC
• Version: 1.0.4

Overview

The Pendo functions fit the stated purpose, but automatic installation can execute unchecked code and introduce broader changes to your agent’s skills.

Review the CLI setup before installing. Prefer a verified, fixed release installed under your control, and disable automatic skill synchronization with OO_SKILLS_SYNC_DISABLED=1 if unwanted. Connecting Pendo gives OOMOL access through your integration credentials. The external installers and hosted backend were not validated; no malicious behavior was established in the bundled artifact.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The supplied command invokes an Oomol-hosted installer rather than accessing Pendo data. Nothing in the chunk establishes that this is a supporting implementation detail for Pendo functionality. The downloaded script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High

• Category: Supply Chain
• Confidence: 98% confidence

Finding

The setup command downloads a mutable remote script and immediately executes it with the agent process's privileges, without version pinning, signature verification, or inspection; the PowerShell alternative follows the same pattern. Compromise of the installer distribution could therefore allow arbitrary code execution and access to local data or credentials, although limiting installation to a missing-CLI error reduces exposure.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

• oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

  bash

  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  

  powershell

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 80)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