Back to skill

Security audit

Cinema Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a redacted cinema-ticketing catalog that maps cinemas to separate mode plugins, with no executable code or hidden credential handling in the inspected artifact.

Install this as a catalog only if you intend to use the referenced cinema ticketing mode plugins. Review the separate mode packages before enabling capture, replay, coupon, failure, or page-world actions, because this package delegates executable behavior to them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
- `SKILL.md`: this operational contract.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest enumerates all user-facing skillName values in Chinese, and there is no accompanying field indicating that the suite is China-specific or that users can opt into this locale. For a broadly installable skill manifest, hard-coding one language for all listed skills can violate language/locale policy when no explicit choice or justification is provided.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The provided manifest context describes a production cinema ticketing catalog with capabilities like capture, replay, coupon binding, and failure handling, while this plugin file's description merely says it is a collection of cinema skills and agent-mode plugins. In the actual file, the only behavior expressed is plugin registration metadata and delegation to another manifest via suiteManifest, so the stated capability scope here does not match what this file itself defines.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description text is entirely in Chinese, and the file provides no indication that language selection is optional or that the plugin is intended only for a Chinese-speaking or region-specific environment. This can violate language or locale policy expectations when users are not given an explicit choice.

Content

No source excerpt is available for this finding.