Security audit

Seedance2.0 视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real AI Hive video-generation skill, but it needs review because endpoint configuration and download handling can expose credentials/media or overwrite local files under hostile responses.

Review before installing. Use only with media you are willing to send to AI Hive, avoid custom base URLs unless you fully trust the endpoint, protect and rotate the API key if endpoint configuration may have been changed, and choose a dedicated output directory because hostile API responses could otherwise overwrite user-writable files until the path handling is fixed.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/videogen.py:91
Finding: Arbitrary API Base URL Can Redirect API Credentials and User Data
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/videogen.py:398
Finding: Remote Task Metadata Can Escape the Output Directory During Downloads
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:171
Finding: Third-Party Dependency Is Installed Without Version or Integrity Pinning
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (11)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file contains substantive skill-facing documentation entirely in Chinese, including feature descriptions and operational notes, but does not indicate that language is optional or limited to a specific locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill declares no explicit tool scope while its documented behavior requires network, file read/write, environment access, and shell execution. Without a least-privilege permissions block, an orchestrator may grant broader capabilities than necessary, increasing the blast radius if the skill is mis-invoked or abused to exfiltrate local files, overwrite data, or make unintended outbound requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description contains extremely broad trigger terms spanning many unrelated brands, platforms, and generic video-creation intents, making accidental activation likely. Overbroad matching can route users into a skill that uploads media, uses API credentials, and submits paid generation jobs even when the user only wanted comparison, pricing, or general discussion.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The documentation says user media will be automatically uploaded and generated files automatically downloaded/saved, but it does not prominently require informed user consent or warn about data transmission and local storage. This can expose sensitive media, audio, or embedded metadata to third-party services and persist potentially sensitive outputs on disk without the user's clear understanding.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The repeated language that the skill is 'also suitable as a search result/entry' creates ambiguous activation boundaries and encourages invocation for loosely related requests. In context, this is risky because the skill is capable of media upload, remote API calls, local file writes, and cost-incurring operations, so vague routing criteria can lead to unintended side effects.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file is presented and packaged as a Seedance2.0 video skill, but the module actually implements a broad AI Hive client for chat, image, video, model listing, uploads, and account queries. This scope mismatch violates least privilege and can let a caller use the skill as a generic AI gateway beyond the declared purpose, increasing the attack surface and policy bypass risk.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The module docstring explicitly describes a 'general AI capability tool', contradicting the declared Seedance2.0 video-only skill intent. In this context, the mismatch is a strong indicator that the implementation may intentionally or accidentally provide broader capabilities than reviewers, orchestrators, or users expect.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The applicability statement explicitly targets '中文或英文用户', which is permissive, but the overall instructions and setup are predominantly Chinese and do not present a clear language-selection mechanism. This can be a locale-policy concern if organizational policy requires not forcing a specific language or locale without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The placeholder string "请替换为你的APIKey" is presented only in Chinese, which imposes a specific language in a user-facing configuration example. The policy allows locale constraints only when justified or when users are given a choice, neither of which is present here.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill exposes a user-info command that retrieves account and wallet details even though the declared purpose is video generation/editing. In a skill context, unrelated account-inspection capability can leak billing or identity metadata and broadens what an attacker or confused agent can do with the provided API key.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The models command enumerates TEXT, IMAGE, and VIDEO models, which exceeds the stated Seedance-specific video purpose. This can aid capability discovery and make it easier to repurpose the skill for unrelated operations, especially when combined with the generic chat/image code present in the same file.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.