Back to skill

Security audit

Gong

Security checks for vulnerabilities and agentic risk

Overview

The Gong read functions fit their purpose, but fallback setup directs the agent to execute an unverified remote installer without separate user approval.

Review the fallback installer before use. Install a verified CLI release yourself or require explicit approval before the agent installs it, and ensure your organization permits OOMOL to access Gong data. No artifact evidence establishes malicious intent, but the remote installer's behavior remains 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
  • 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 installer execution rather than Gong data access. Nothing in the chunk establishes this installer as a supporting dependency for the declared Gong functionality. The downloaded script is not provided, so its subsequent behavior cannot be determined.

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 into Bash executes mutable remote code with the agent process's local privileges, without artifact pinning or independent integrity verification. Compromise of the distribution endpoint or release pipeline could expose locally accessible data or modify the system; the PowerShell alternative has the same underlying risk, despite the legitimate dependency-installation context.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The fallback setup instructs the agent to execute a downloaded installer without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to execute a remote installer without first obtaining approval for local code execution and system changes, which exceeds the normal expectations of a Gong read request. Requiring a missing-CLI error limits when this occurs, but does not authorize installation or explain its risks; actual execution also depends on the host's tool 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 81)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