Back to skill

Security audit

Render

Security checks for vulnerabilities and agentic risk

Overview

The Render workflow includes approval safeguards, but setup can execute unpinned downloaded code and introduce additional agent skills without clearly requesting approval.

Review setup before installing: approve CLI installation separately, verify the chosen release, and review or disable automatic bundled-skill synchronization. OOMOL will mediate access to your connected Render account. Keep the existing confirmation requirements for deployments, restarts, rollbacks, and suspensions. The Review verdict concerns setup authority and under-disclosed persistent changes; no malicious behavior 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 command installs software from Oomol and contains no Render API interaction or resource-management behavior. Nothing in the supplied chunk establishes this installation as a supporting dependency for Render operations, so its demonstrated purpose materially differs from the declared description.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes whatever the installation endpoint serves with the invoking user's permissions. A compromised distribution endpoint or malicious installer update could therefore access local secrets or modify files; HTTPS does not protect against a compromised publisher, and the PowerShell alternative has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Fallback setup instructs execution of remote installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell code without explaining its local-system effects or requiring installation approval. Restricting this path to a missing CLI reduces exposure, but a Render request does not necessarily authorize installing software; this overlaps with the remote-execution risk in SC2.

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 85)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