Back to skill

Security audit

巨物与微缩奇观广告|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it claims, but it handles an API key and media transfers with under-scoped network controls that users should review before installing.

Install only if you trust this AI-HIVE workflow and are comfortable with persistent API-key storage. Avoid custom AI_HIVE_BASE_URL or --base-url values, inspect ~/.ai-hive/config.json before use, use a revocable/limited API key where possible, and upload only media you are authorized to share with the service.

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

AI-HIVE API Key Can Be Forwarded to an Arbitrary Endpoint

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:267
Finding

Unvalidated Server-Controlled URLs Enable Media Diversion and Client-Side Request Forgery

Content
View full analysis
PUT -> complete. Returns mediaId.""" path = Path(file_path) if not path.is_file(): raise SystemExit(f"File does not exist: {file_path}") filename = path.name content_type = guess_mime(str(path)) size = path.stat().st_size print(f"[1/3] Creating upload credential: {filename} ({content_type}, {size} bytes)") token = client.create_upload_token(filename, content_type, size) media_id = token["mediaId"] upload_url = token["upload"]["url"] upload_method = token["upload"].get("method", "PUT") upload_headers = token["upload"].get("headers", {}) # Upload to object storage without the API key, using returned headers print(f"[2/3] Uploading file to object storage...") with open(str(path), "rb") as f: try: oss_resp = requests.request( upload_method, upload_url, headers=upload_headers, data=f, timeout=300, ) except requests.exceptions.RequestException as e: raise SystemExit( f"Object-storage upload network error: {e}\n" "Check the network connection or whether the file is too large" ) ``` The original source uses Chinese user-facing strings; the logic above is otherwise reproduced without changing the vulnerable request behavior. ```python def download_file(url, out_path, timeout=300): """Stream a file download with progress display.""" print(f"[download] {out_path.name}") try: resp = requests.get(url, stream=True, timeout=timeout) resp.raise_for_status() total = int(resp.headers.get("content-length", 0)) downloaded = 0 with open(st ...[truncated 2885 chars]
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

A second description-behavior mismatch indicates the skill is presented as a specialized ad-generation workflow but may only perform generic local video editing. In security terms, capability misrepresentation undermines trust boundaries: operators may permit file, shell, or network access for a supposedly necessary workflow, yet the real behavior is different and therefore harder to justify, monitor, and constrain safely.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A second description-behavior mismatch indicates the skill is presented as a specialized ad-generation workflow but may only perform generic local video editing. In security terms, capability misrepresentation undermines trust boundaries: operators may permit file, shell, or network access for a supposedly necessary workflow, yet the real behavior is different and therefore harder to justify, monitor, and constrain safely.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill advertises and demonstrates operations that imply access to environment variables, local files, network endpoints, and shell execution, but it does not declare a restrictive tool scope such as permissions or allowed-tools. In an agent setting, this creates an overbroad execution surface where a caller may trigger sensitive capabilities beyond what reviewers or operators expect, increasing the chance of secret exposure, arbitrary file access, or unintended outbound requests.

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 ('production-ready Chinese workflow') regardless of the user's language preference. This can override user intent, reduce transparency, and increase the chance that safety-critical instructions or review outputs are produced in a language the user cannot verify, especially in a skill that generates executable workflow steps and commands.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This Python file embeds the skill name, CLI description, and search aliases entirely in Chinese, which indicates a fixed language/locale experience. The file does not offer any user-selectable language option or explain a justified region-specific constraint, so it appears to violate the language/locale policy for natural-language behavior.

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:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code file contains natural-language user-facing descriptions and instructions entirely in Chinese, including the top-level docstring and CLI help text, with no indication that users may choose another language. Under the policy for natural-language content in any file type, forcing a specific language without opt-in is a locale-policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language instructions, triggers, and output requirements are all presented in Chinese, and the file does not indicate that users may choose another language. Under the stated policy, forcing a specific language without opt-in is a locale/language policy concern unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.