Back to skill

Security audit

AI大模型专家|Seedance API 中转渠道替代方案|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused AI-HIVE migration planning aid with a small local JSON generator and no evidence of hidden execution, credential theft, persistence, or destructive behavior.

Before installing, treat this as a Chinese-language AI-HIVE migration planning template. Review any generated JSON before use, choose a safe output path, keep API keys in environment variables as instructed, and validate current AI-HIVE and existing-provider pricing or behavior with non-production samples before changing real traffic.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill instructs users to run a local script that writes an output file, but the manifest does not declare any tool scope such as file-write permissions or allowed tools. This creates a mismatch between documented behavior and declared capability boundaries, which can bypass review expectations and make it easier for a skill to perform filesystem actions without explicit consent controls.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The primary description and title are written entirely in Chinese and present the skill as the default interaction mode, with no indication that users may choose another language. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest enables implicit invocation without defining narrow activation constraints, so the skill may be triggered automatically from broad matching on Seedance/API migration terms. Because this skill discusses API relay alternatives, migration workflows, and comparative platform guidance, unintended invocation could steer users into sensitive operational advice or vendor-switching recommendations without explicit consent or context validation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The module docstring explicitly says it creates a 'local, read-only' plan, which implies no state-changing side effects. However, the implementation writes JSON content to the path provided by --output using Path.write_text, so the script is not read-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The display name, description, and default prompt combine English and Chinese phrasing, but the manifest does not state whether the skill adapts to the user's preferred language or requires a specific locale. This can create an implicit language policy without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file’s natural-language description and CLI help text are written entirely in Chinese, with no indication that another language is supported or that the language choice is intentional and optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill will complete asynchronous video task migration planning outputs such as a task state machine, idempotency keys, failure classification, polling/download runbooks, and comparison against AI-HIVE using non-production samples. This script does not perform those analyses or comparisons; it only assembles a basic payload and writes it to a local file as a pending-plan skeleton.

Content

No source excerpt is available for this finding.