Back to skill

Security audit

Seedance 2.0 提示词专家|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a disclosed AI-HIVE video-generation helper, but it handles API keys and billable remote operations with an unsafe custom endpoint option.

Review this before installing if you plan to use real AI-HIVE credentials. Use only the default AI-HIVE endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you fully trust the endpoint, and expect the skill to store an API key locally and submit paid generation jobs only after explicit confirmation.

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

Bearer API Key Can Be Transmitted to an Arbitrary Configured Server

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/videogen.py:10
Finding

Unpinned Runtime Dependency Installation Guidance

Content
View full analysis
Remediation
View remediation
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 (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

This finding indicates the skill may perform broader functions such as generic chat, wallet or user info retrieval, image generation, browser opening, or API-key initialization without declaring them in its purpose. Hidden or undeclared capabilities are risky in a skill that already references billable API use, because they can lead to privacy issues, account data exposure, unexpected network activity, or social engineering around secrets.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This finding indicates the skill may perform broader functions such as generic chat, wallet or user info retrieval, image generation, browser opening, or API-key initialization without declaring them in its purpose. Hidden or undeclared capabilities are risky in a skill that already references billable API use, because they can lead to privacy issues, account data exposure, unexpected network activity, or social engineering around secrets.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 77)May include surrounding context.

md
python3 scripts/videogen.py init --skill-name seedance-2-prompt-expert-ai-hive

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
python3 scripts/videogen.py init --skill-name seedance-2-prompt-expert-ai-hive

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises executable workflows and includes code examples that use environment variables, local files, network access, and shell commands, yet it declares no explicit tool scope or permission boundaries. In an agent environment, this can cause the skill to receive broader capabilities than users expect, increasing the chance of unintended file access, network calls, secret exposure, or costly external actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and instructions are entirely in Chinese and do not indicate that the user may choose another language for interaction or output. Under the language/locale policy, this can be a natural-language policy issue unless the locale restriction is explicitly justified or made optional.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation triggers include broad everyday terms such as '视频提示词', '文生视频', and '图生视频', which can cause the skill to activate in many unrelated conversations. Over-broad triggering is dangerous because it can route users into a skill that encourages external API usage, file handling, or billable generation flows when they did not explicitly ask for this specific service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The default prompt hard-codes Chinese output and a specific production style without checking user preference. This is primarily a prompt-governance issue: it can reduce user control, cause misunderstanding, or mask intent in multilingual contexts, but it is not inherently a direct security exploit on its own.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest enables implicit invocation without any visible activation constraints, allowing the skill to be triggered in broader contexts than a user may expect. Because this skill can generate production-ready workflows and runnable AI-HIVE commands, overbroad auto-selection increases the chance of unintended use, prompt-scope confusion, or unsafe assistance being surfaced without clear user intent.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file advertises and implements a broad AI-Hive client with chat, image generation, model enumeration, uploads, and user-info retrieval, which exceeds the declared Seedance 2.0 prompt/video scope. In an agent-skill context, this expands the accessible attack surface and can enable unauthorized capability use, account reconnaissance, or policy bypass by invoking hidden generic functions not implied by the 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 code file contains natural-language descriptions and user-facing instructions entirely in Chinese, presenting the tool as a general-purpose skill rather than a clearly region-specific one. Under the language/locale policy, forcing a specific language without offering user choice or documenting a justified locale constraint is a policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The embedded generic parser and command map expose user-info, models, chat, image, video, task, and upload operations, allowing callers to interact with non-Seedance models and inspect account data beyond the skill's stated purpose. In practice this creates a confused-deputy problem: a user or upstream agent may believe they are invoking a narrow Seedance helper while the code actually grants much broader API reach.

Content

No source excerpt is available for this finding.