ClawHub
Back to skill

Security audit

Apidot Wan 2 7 Image Api

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only APIDot Wan 2.7 Image skill with no executable code, persistence, or hidden credential handling.

Installers should understand this skill is meant to steer APIDot Wan 2.7 Image documentation and integration work. Do not put APIDot API keys in frontend code, logs, public repositories, screenshots, or chat output, and make live API calls only from a controlled server-side environment.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The search terms include ambiguous phrases like 'Wan image generation' and 'Wan image editing' that can overlap with general user requests unrelated to this exact provider or model. This increases the risk of accidental skill activation and inappropriate tool routing, especially where multiple image-related skills coexist.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill's 'When To Use' section is broad enough to match many ordinary image-generation or editing requests without clearly constraining invocation to APIDot-specific intent. In an agent ecosystem, that can cause over-triggering and unintended routing to this skill, which may misdirect users, bias answers toward a third-party service, or suppress better-matched skills.

Content

No source excerpt is available for this finding.