Back to skill

Security audit

Seedance AI视频导演|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its AI video workflow purpose, but it handles API keys, media uploads/downloads, and local file writes with weak controls that users should review before installing.

Review before installing. Use only the default AI-HIVE endpoint unless you fully trust a custom endpoint, prefer a limited or test API key, do not upload sensitive media unless you trust the service, choose a dedicated output folder, and confirm parameters before any billable generation. Be aware that local ffmpeg edits and downloads can overwrite files if paths collide.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:93
Finding

API Credential Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:278
Finding

Untrusted Server-Controlled Upload and Download Destinations

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:389
Finding

Path Traversal and Unintended File Overwrite Through Server-Controlled Filename Components

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/edit_video.py:59
Finding

Forced Overwrite in Local Video Editing Operations

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill description promises a high-level AI directing and AI-HIVE integration workflow, but the detected behavior does not implement those capabilities and instead appears centered on lower-level local video handling. This mismatch is dangerous because users or supervising agents may authorize the skill under false assumptions, leading to unsafe trust decisions, unintended file operations, or hidden capability creep outside the stated purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises executable workflows involving environment variables, filesystem access, networking, and shell commands but does not declare any explicit tool scope or permissions boundary. In an agent environment, this can lead to overbroad runtime authority, making it easier for the skill to access sensitive data, modify local files, or invoke external services without clear review or restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and title are written as Chinese-only skill framing for invocation and use, and the usage section later treats language as an input parameter rather than offering a user-facing choice for the skill's own responses. This can violate language/locale policy when a skill implicitly forces a specific language without explicit opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest's default_prompt explicitly requires a "production-ready Chinese workflow," which imposes a specific language choice regardless of the user's preference. This is a natural-language locale policy issue because the file does not offer an opt-in or alternative language selection.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/edit_video.py (reported line 20)May include surrounding context.

python
def run(args: list[str]) -> None:
    print(" ".join(args))
    subprocess.run(args, check=True)


def main() -> None:

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest describes a skill focused on producing reviewable directing plans and, when generation is needed, interacting with AI-HIVE OpenAPI for configuration lookup, upload, pricing, routing, polling, and download. This script instead performs direct local media transformations with ffmpeg (trim, aspect conversion, mute, loudness normalization, concat), which is a separate video-editing capability not described as part of the skill's purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file is presented as a Seedance video-director skill, but it exposes a broad, general-purpose AI Hive client with chat, image, video, model listing, upload, and account-related capabilities. This capability overreach violates least privilege and increases the attack surface: an agent invoking this skill could perform actions unrelated to the declared purpose, including arbitrary model access and media handling.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes a user-info endpoint that can retrieve account information and wallet balance, which is unrelated to generating Seedance directing outputs. In a broader agent environment, unnecessary access to billing/account metadata increases privacy exposure and can aid reconnaissance about the user's subscription state or available funds.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest promises a safety/cost-control workflow of producing a reviewable directing plan before expensive generation, but the implementation directly submits generation requests with no review gate, confirmation step, or policy enforcement. In an agent setting, this can lead to unintended costly actions or bypass of human review expectations embedded in the skill description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language descriptions and CLI guidance entirely in Chinese, including the module docstring and most user-facing output. Because the skill does not offer a language/locale choice or document that it is intentionally region-specific, it may violate a language/locale policy requiring user opt-in.

Content

No source excerpt is available for this finding.