ClawHub
Back to skill

Security audit

composition-eight-questions

Security checks for vulnerabilities and agentic risk

Overview

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

Safe to install for photography composition help. Users may want the publisher to clarify whether responses should follow the user's language, but the inspected artifacts do not show risky permissions or unsafe actions.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file includes parallel Chinese and English invocation guidance and trigger phrases, but nowhere states whether the skill should respond in one language, respect the user's current language, or ask for preference. Under the language/locale policy, forcing or assuming a language behavior without opt-in can create an unclear or noncompliant user experience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This manifest-style test file contains natural-language expectations that require the skill to respond in Chinese (e.g. "调用 ... 系统讲解...") while one test prompt is in English. That creates a language-policy issue because the skill appears to enforce a specific language/locale without offering the user a choice or documenting justified locale constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.