Security audit

Seedance 首尾帧生视频

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its video-generation purpose, but it needs review because it has broad activation text and weak safeguards around API keys, uploads, and downloaded files.

Install only if you intend to use AI Hive for this specific video workflow. Avoid using custom base URLs unless you fully trust them, prefer environment or config-based secret handling over command-line keys, review uploads before running generation, and choose an output directory where overwrites would not be harmful.

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: Bearer API Key Can Be Disclosed to an Untrusted Configurable Endpoint
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/videogen.py:395
Finding: Generated Files Can Escape the Selected Output Directory
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:180
Finding: Dependency Installation Instructions Use an Unpinned Package
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)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The description uses very broad trigger phrases spanning generic AI video, competitor names, pricing, APIs, and migration queries, making the skill likely to activate for many loosely related requests. Overbroad activation can route unrelated user tasks into a skill that uploads media, handles credentials, and writes files, increasing the chance of unintended sensitive actions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The applicability section massively expands scope to unrelated brands, platforms, ad products, e-commerce channels, and marketing contexts without hard boundaries. In context, this is risky because the skill is not merely informational—it can upload user media, initialize API credentials, submit jobs, and save outputs, so accidental invocation can lead to unintended data transmission and costs.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill documents and invokes capabilities equivalent to shell execution, network access, reading environment/configuration, and local file writes, but it declares no explicit tool scope or permission boundaries. That creates a confused-deputy risk where the agent may execute powerful actions without transparent least-privilege constraints or user-aware gating.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill states that it will automatically upload user media, track tasks, and download/save generated videos, but it does not prominently warn that local files will be transmitted to a remote service and that outputs will be written locally. This weakens informed consent and may expose sensitive images, videos, or filesystem contents through routine use.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The documentation walks users through obtaining, copying, and storing an API key, including browser-assisted initialization and persistent storage in config files, but does not provide strong warnings about secret handling. This increases the likelihood of credential exposure through shell history, logs, screenshots, clipboard leakage, or insecure local environments, enabling unauthorized API use and billing abuse.
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 as a narrowly scoped Seedance first/last-frame video skill, but it actually embeds a full generic AI Hive client with broader capabilities. This violates least privilege and increases the attack surface: a caller or wrapper that assumes only fixed video generation may unknowingly expose model discovery, chat, image generation, and account-related operations.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The top-level docstring says this is a '通用 AI 能力调用工具' that wraps text chat, image generation, video generation, model query, media upload, and task polling. That directly conflicts with the skill's declared purpose as a fixed Seedance 首尾帧生视频 skill, because the documentation asserts a much broader intent than the actual skill manifest.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This Python file contains user-facing natural-language strings entirely in Chinese, starting from the module docstring and continuing through CLI help and prompts. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The presence of user-info and model-listing/discovery capabilities is unrelated to the declared purpose of generating Seedance first/last-frame videos. In a skill context, extra account/discovery functionality can leak wallet/account metadata, expose broader platform capabilities to downstream agents, and enable misuse beyond the user's expected permission scope.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Implementing generic chat and image-generation operations inside a skill marketed as fixed-function video generation creates hidden capability expansion. That makes policy enforcement harder and can let an agent repurpose the skill for unintended content generation or data handling paths that were never reviewed for this use case.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file contains user-facing natural-language content exclusively in Chinese across the substantive changelog entries. Under the policy rule for language/locale handling, forcing a specific language without opt-in or justification can be a policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.