Back to skill

Security audit

movie-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a movie/TV search helper, but it is designed to surface torrent and download-site links broadly and without clear legality or safety warnings.

Review before installing. This skill may lead the agent to provide links to torrent or unofficial download sites for movies and shows, which can create copyright, malware, and unsafe-browsing risk. Prefer a version that defaults to licensed platforms and asks before showing unofficial download resources.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger is explicitly designed to activate on broad natural-language phrases and even states the skill should be used without an explicit skill invocation. That creates overreach risk: the agent may route ordinary movie-related queries into a piracy-oriented workflow without clear user consent, increasing the chance of policy-violating or unsafe assistance.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill presents itself as a general movie-search tool, but its workflow prominently returns torrent, magnet, and download links from piracy-associated sites without warning the user. This concealment makes misuse more likely and can cause the agent to facilitate copyright infringement or direct users to risky third-party sites under the guise of normal content discovery.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This eval expects the response in Chinese ("返回 ...") even when the user prompt on L16 is in English. That imposes a language choice without user opt-in, which matches the language/locale policy violation criteria for natural-language content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.