ClawHub
Back to skill

Security audit

auto-exposure-limitation

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped photography instruction skill with no executable code, network use, credential access, persistence, or hidden authority.

Safe to install from a security perspective. Expect the skill to answer mainly in Chinese and to provide educational photography guidance, not camera automation or exact exposure settings. The malformed test-prompts.json should be fixed by the publisher for reliable testing.

A.I.G

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

SkillSpector

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON file is a manifest-like test file, so natural-language policy checks apply. The prompts and expected behaviors consistently assume Chinese output/interaction, but the file does not indicate that this skill is intentionally region-specific or that users can opt into the locale, which can constitute a language/locale policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.