Back to skill

Security audit

用户访谈转客户案例视频|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real AI-HIVE video workflow, but its API client handles credentials, custom endpoints, uploads, downloads, and overwrites with insufficient guardrails.

Review this before installing if you will use real API keys or business media. Use only the official AI-HIVE endpoint, avoid setting AI_HIVE_BASE_URL or custom base_url values unless you fully trust the server, keep API keys out of logs and repositories, choose output paths carefully because existing files may be overwritten, and run downloads/uploads only for media you are allowed to share.

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 (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:94
Finding

Bearer Credential Disclosure Through an Unrestricted API Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:273
Finding

Unvalidated Server-Directed Upload and Download URLs

Content
View full analysis
" raise SystemExit(f"OSS 上传失败 ({oss_resp.status_code}): {detail}") ``` ```python def download_file(url, out_path, timeout=300): """流式下载文件,带进度条显示。""" 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(str(out_path), "wb") as f: for chunk in resp.iter_content(chunk_size=8192): if chunk: f.write(chunk) downloaded += len(chunk) if total > 0: pct = int(downloaded * 100 / total) bar = "█" * (pct // 5) + "░" * (20 - pct // 5) print(f"\r {bar} {pct}% ({downloaded // 1024}KB)", end="", flush=True) print() size_mb = downloaded / (1024 * 1024) print(f"[ok] {out_path} ({size_mb:.1f} MB)") except requests.exceptions.RequestException as e: print(f"\n[error] 下载失败: {e}", file=sys ...[truncated 2691 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/edit_video.py:58
Finding

Silent Overwrite of Existing Video Output Files

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/videogen.py:21
Finding

Unpinned Third-Party Dependency Installation Guidance

Content
View full analysis
Remediation
View remediation
--hash=sha256:`. - Pin and hash transitive dependencies as well. - Recommend installation inside a dedicated virtual environment. - Configure installation from a trusted package index and avoid untrusted mirrors. - Use a lock-generation tool and establish a regular dependency-review and update process. - Add automated vulnerability scanning for direct and transitive Python dependencies. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (11)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This finding indicates the skill may expose undeclared generic chat, image generation, wallet/user-info access, and broader model-query functionality while lacking enforcement of its own stated safety limits around authorization and fake testimonials. In a content-production context, undeclared access to account data or general generation tooling materially raises the risk of privacy issues, billing abuse, deceptive content creation, and policy circumvention.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding indicates the skill may expose undeclared generic chat, image generation, wallet/user-info access, and broader model-query functionality while lacking enforcement of its own stated safety limits around authorization and fake testimonials. In a content-production context, undeclared access to account data or general generation tooling materially raises the risk of privacy issues, billing abuse, deceptive content creation, and policy circumvention.

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 expose undeclared generic chat, image generation, wallet/user-info access, and broader model-query functionality while lacking enforcement of its own stated safety limits around authorization and fake testimonials. In a content-production context, undeclared access to account data or general generation tooling materially raises the risk of privacy issues, billing abuse, deceptive content creation, and policy circumvention.

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 involving environment variables, local file access, shell commands, and network/API usage, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this increases the chance of over-broad tool access, making unintended file reads/writes, secret exposure, or arbitrary command/network actions more likely if the skill is invoked or extended incorrectly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and title are written entirely in Chinese and define invocation examples only in Chinese terms, which creates an implicit language/locale constraint. The file does not offer users a language choice or explain that the skill is intentionally limited to a Chinese-speaking or region-specific environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The default prompt hard-codes a Chinese-language response style ('production-ready Chinese workflow') without checking the user's language preference. This can override user intent, reduce transparency, and create prompt steering behavior that is especially undesirable in a generally invocable skill because it changes output characteristics automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The user-facing description, argument parser description, skill name, and search aliases are all presented only in Chinese. This creates an implicit language constraint without any opt-in, alternative locale, or documentation that the skill is intentionally region-specific.

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:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest describes a narrowly purposed skill for transforming authorized customer interviews into case-study videos, but this file implements broad-purpose OpenAPI operations including free-form text chat, generic image generation, model enumeration, user-info lookup, and arbitrary media upload. Those capabilities go beyond an implementation detail of the stated workflow and materially widen what the skill can do.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The top-level docstring says this is a '通用 AI 能力调用工具' and explicitly documents text chat, image generation, video generation, model queries, media upload, and polling. That directly conflicts with the specialized skill identity and manifest framing focused on customer interview evidence extraction and case-video production rather than a general AI toolbox.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This Python file contains natural-language docstrings, prompts, help text, and status messages entirely in Chinese, including the main skill description and operational instructions. Under the policy, locale-specific language requirements should not be forced without user opt-in or a clearly documented regional justification, and no such choice or justification appears here.

Content

No source excerpt is available for this finding.