Back to skill

Security audit

Runpod

Security checks for vulnerabilities and agentic risk

Overview

The Runpod workflow has clear approval checks, but automatic setup can execute an unchecked installer with broader effects on your agent.

Review and install the CLI separately before using this skill. Check and, if unwanted, disable its cross-agent skill synchronization using the [documented controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Use narrowly scoped Runpod credentials and retain approvals for changes and deletions. The external installers and hosted connector were not audited.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command installs software by piping a remote script directly into Bash. It contains no Runpod operations or evidence connecting this installation to the declared purpose. 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 pipes a remotely retrieved, unpinned script directly into Bash, allowing its contents to execute with the agent's local permissions without prior review or integrity verification. A compromised hosting endpoint or installer could steal accessible credentials or modify local files; the missing-CLI condition limits exposure but does not mitigate that execution risk.

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