Back to skill

Security audit

exposure-dual-control

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed photography guidance skill with no code execution, data access, persistence, or privileged behavior.

Before installing, note that this skill is mainly written in Chinese and may steer responses toward that language unless the agent follows the user's language preference. Security-wise, it is a low-risk educational prompt skill.

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

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest-style description and trigger list hard-code both Chinese and English phrasing, but the skill does not state whether users may interact in their preferred language or whether multilingual triggering is optional. Under the policy rule, language handling should either be explicitly user-selectable or clearly justified as a locale-specific skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This JSON file contains natural-language expectations that require the skill response to be in Chinese even when the user prompt is in English. That can violate a language/locale policy because the file does not indicate any user opt-in or justified locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.