Sonarr Fixed

• Outcome: Pass
• Latest audit: May 28, 2026 at 8:14 AM UTC
• Version:
  1.0.2

Overview

This skill is a disclosed Sonarr control wrapper, but it can remove shows and optionally delete media files if an agent is allowed to run those commands.

Install only if you want an agent to manage your Sonarr library using your Sonarr API key. Confirm every remove action yourself, and treat --delete-files as destructive because it can delete associated media files through Sonarr.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill explicitly instructs users to run shell commands (`bash scripts/sonarr.sh ...`) but does not declare corresponding permissions/capabilities in its manifest. This creates a transparency and policy-enforcement gap: a reviewer or runtime may underestimate what the skill can do, even though it can invoke local scripts that interact with external services and potentially modify state.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 93% confidence
• Finding: The declared purpose says the skill searches for and adds TV shows, but the documented commands also support existence checks, configuration enumeration, removal, and optional file deletion. This mismatch is dangerous because it hides destructive capabilities behind a narrower description, increasing the chance that users or automated systems authorize the skill without realizing it can remove media and delete files.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The skill metadata and description omit the documented removal capability, including an option to delete files. Omitting destructive behavior from the manifest weakens informed consent and security review, because consumers may treat the skill as read/add-only when it can also perform irreversible state changes.

Description-Behavior Mismatch

High

• Confidence: 98% confidence
• Finding: The skill metadata says it searches and adds TV shows, but the script also implements a remove command that can delete series and, with --delete-files, remove associated media files from Sonarr-managed storage. This hidden destructive capability increases the risk of user deception, unsafe agent invocation, and unintended data loss because consumers of the skill are not informed that deletion is possible.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The remove path performs an irreversible DELETE request and supports deleteFiles=true without any interactive confirmation, secondary flag validation, or safety interlock at execution time. In an agent setting, a mistaken parameter, prompt injection, or user misunderstanding could immediately remove shows and optionally erase files, causing avoidable data loss.

VirusTotal

64/64 vendors flagged this skill as clean.