Back to skill

Security audit

小红书爆款视频拆解|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed AI-HIVE video workflow helper, but its API-key handling can send credentials to an arbitrary configured server, which warrants Review before installation.

Install only if you are comfortable giving this skill an AI-HIVE API key and uploading selected media to AI-HIVE. Use the default AI-HIVE endpoint only, avoid custom --base-url or AI_HIVE_BASE_URL values, consider a restricted or disposable API key, confirm all billable generation parameters before running, and install dependencies in a virtual environment.

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:92
Finding

API Key Disclosure Through an Unrestricted API Base URL

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/videogen.py:1
Finding

Unpinned Third-Party Dependency Installation Guidance

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (14)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

If the skill exposes generic chat, image generation, account-information retrieval, model listing, pricing access, or interactive API-key setup beyond its declared niche purpose, that expands the attack surface significantly. Undeclared access to account metadata or credential-setup flows can enable unintended data exposure, overbilling, or abuse because users may invoke the skill under the assumption it is narrowly scoped to Xiaohongshu decomposition tasks.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

If the skill exposes generic chat, image generation, account-information retrieval, model listing, pricing access, or interactive API-key setup beyond its declared niche purpose, that expands the attack surface significantly. Undeclared access to account metadata or credential-setup flows can enable unintended data exposure, overbilling, or abuse because users may invoke the skill under the assumption it is narrowly scoped to Xiaohongshu decomposition tasks.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

If the skill exposes generic chat, image generation, account-information retrieval, model listing, pricing access, or interactive API-key setup beyond its declared niche purpose, that expands the attack surface significantly. Undeclared access to account metadata or credential-setup flows can enable unintended data exposure, overbilling, or abuse because users may invoke the skill under the assumption it is narrowly scoped to Xiaohongshu decomposition tasks.

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 xiaohongshu-viral-video-decomposer-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 xiaohongshu-viral-video-decomposer-ai-hive

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file presents itself as a Xiaohongshu viral-video decomposition skill, but the implementation is a broadly capable AI Hive client that can upload arbitrary media and invoke generic text/image/video generation. This mismatch increases the attack surface and can mislead users or orchestrators into granting broader capabilities than the declared purpose requires, enabling unauthorized or policy-violating content generation under a narrower-looking skill label.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises executable workflows that rely on environment variables, file access, network access, and shell-driven local processing, but it does not declare any explicit tool scope or permission boundaries. That makes the operational capability opaque to the host and reviewers, increasing the chance of overbroad execution, secret exposure, or unsafe file/network actions if the skill is enabled.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger conditions are broad enough to match many generic business-content requests, which can cause this skill to activate outside its intended scope. Over-broad routing is dangerous because it may steer unrelated user tasks into a skill with network, file, shell, or media-processing capabilities, increasing the chance of unnecessary data handling, unintended external API use, or billable actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The default prompt explicitly instructs the skill to produce a "production-ready Chinese workflow," which imposes a specific language on users. This is a natural-language policy concern because the file does not indicate that Chinese is optional, user-selected, or justified as a region-specific requirement.

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:

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring explicitly describes a generic AI capability tool, contradicting the advertised identity of a specialized Xiaohongshu decomposition skill. This kind of identity inconsistency is dangerous because security reviewers, agents, or users may trust the package based on its narrow branding while the code actually enables broader operations.

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 includes its primary docstring, CLI descriptions, prompts, and status messages in Chinese, making the skill effectively Chinese-only by default. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Exposing unrelated functions such as model enumeration, wallet/user-info lookup, text chat, and image generation violates least privilege for a decomposition-focused skill. If an agent can invoke these extra commands, the skill can be used as a general-purpose API proxy, broadening misuse opportunities and potentially exposing account metadata or incurring unexpected costs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file embeds a Chinese-only skill name and description in the module docstring and argparse description, with no indication that users may select another language or locale. This can violate a language/locale policy when a skill implicitly forces one language without opt-in.

Content

No source excerpt is available for this finding.