Back to skill

Security audit

natural-light-direction

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward photography guidance skill about natural light direction, with no code execution, data access, persistence, or hidden high-impact behavior.

Before installing, consider that the skill appears primarily written for Chinese-language photography guidance, though it also lists English triggers. It is otherwise low risk based on the inspected artifacts.

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
89% confidence
Finding

The file’s natural-language content is entirely in Chinese and references a Chinese-titled source book, indicating the skill is designed around a fixed language context. There is no indication that users can choose another language or that the locale restriction is explicitly documented as an opt-in or region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest description and trigger list present activation language in both Chinese and English, but do not clarify whether the skill is intended to operate bilingually by default or based on user preference. This can create a language/locale policy concern if the organization expects the agent to respect the user's chosen language unless explicitly opted into another one.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.