ClawHub
Back to skill

Security audit

Prowlarr

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Prowlarr helper, but users should treat delete, enable/disable, test, and sync commands as real administrative actions.

Install only if you are comfortable giving this skill a Prowlarr API key for the configured instance. Protect the credentials file, prefer a limited or dedicated API key if available, verify indexer IDs before enable/disable/delete, and require clear user confirmation before running delete or sync commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill explicitly instructs the agent to run shell commands (`./scripts/prowlarr-api.sh ...`) but does not declare corresponding permissions or safety boundaries. This creates a capability mismatch where an agent may execute operational or state-changing commands without transparent authorization review, increasing the risk of unintended actions against the Prowlarr service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README instructs users to place a sensitive API key in a plaintext config file and export it via environment variables, but provides no warning about secret handling, file permissions, shell history exposure, or process/environment leakage. In a skill that interacts with a live Prowlarr instance, compromise of this key could allow unauthorized searches and administrative actions against indexers and downstream integrations.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README presents indexer management and sync operations as routine commands without warning that they change Prowlarr configuration and may propagate those changes to connected applications such as Sonarr and Radarr. In this skill context, users may trigger destructive or unintended administrative changes more easily because the documented actions are operational and affect external systems, not just local read-only queries.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill documents a destructive delete operation for indexers without any warning, confirmation requirement, or rollback guidance. In an agentic context, this makes accidental or prompt-induced deletion more likely, potentially disrupting search automation, downstream app integrations, and user configuration.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script exposes a destructive delete operation for indexers and executes it immediately with no confirmation, dry-run, or safeguard. In an agent/tooling context, a mistaken model action, parameter mix-up, or prompt injection could remove indexer configuration and disrupt search/sync operations.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
cmd_delete() {
    local id="$1"
    api DELETE "/indexer/$id"
    echo '{"status": "ok", "indexer": "'"$id"'", "deleted": true}'
}
Confidence
95% confidence
Finding
DELETE "/indexer/$id

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.