Back to skill

Security audit

BunnyCDN

Security checks for vulnerabilities and agentic risk

Overview

The BunnyCDN actions have clear approval controls, but first-time setup directs the agent to execute unverified remote code without separate approval.

Review before installing. Install a pinned, independently verified CLI release yourself and review its automatic skill installation behavior. Connecting BunnyCDN entrusts OOMOL with provider access and request data. Keep cache purges subject to explicit target approval. The remote installer and hosted connector implementation were not verified; no malicious behavior was established in the bundled artifact.

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 performs remote script execution rather than any visible BunnyCDN operation. Nothing in the chunk establishes that the Oomol installer is a supporting dependency for the declared purpose. The downloaded script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote response directly into Bash without pinning or independent integrity verification; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the installer delivery infrastructure could execute arbitrary code with the invoking user's permissions, exposing local files and credentials, although the skill does not explicitly request elevated privileges.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When the CLI is missing, the setup instructions direct the agent to execute a remote installer without first obtaining approval for local software installation or explaining its effects. The missing-command condition limits when this occurs, but the workflow still crosses from a BunnyCDN task into local code execution without an explicit consent boundary.

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 78)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