Back to skill

Security audit

golden-hour

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward photography timing guide with no code, permissions, persistence, or data access.

Installers should expect a Chinese-first photography reference with some English trigger phrases. Review it for usefulness in your preferred language, but it does not appear to access data, run commands, install dependencies, or persist changes.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest-like JSON file contains only Chinese prompts and expected behaviors, indicating the skill is designed to activate and respond in Chinese. Under the policy rules, forcing a specific language without offering user choice or documenting a justified locale restriction is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest description and trigger section present activation guidance in both Chinese and English, but the file does not explain whether the skill should activate based on user language preference or offer an explicit language choice. Under the policy rule for language/locale constraints, undocumented language behavior can create ambiguity about how the skill applies across users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.