Back to skill

Security audit

light-meter-compensation

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent photography guidance skill with no executable code, persistence, credentials, network access, or hidden high-impact behavior.

Safe to install for photography exposure guidance. Users should expect mostly Chinese content with English trigger support; maintainers may want to state language behavior explicitly for clarity.

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
88% confidence
Finding

This manifest-style test file is subject to natural-language policy review. Multiple prompts and expected behaviors are written in Chinese and implicitly require Chinese responses, but the file does not indicate that the skill is region-specific or that language is user-selectable, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest description and trigger list include both Chinese and English phrasing as part of the activation guidance, but there is no statement that the skill supports multiple languages by user choice. Under the policy rule, forcing or implicitly privileging a language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.