T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:94- Finding
Bearer Credential Disclosure Through an Unrestricted API Base URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/videogen.py:94Bearer Credential Disclosure Through an Unrestricted API Base URL
scripts/videogen.py:273Unvalidated Server-Directed Upload and Download URLs
scripts/edit_video.py:58Silent Overwrite of Existing Video Output Files
scripts/videogen.py:21Unpinned Third-Party Dependency Installation Guidance
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.
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.
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.
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.
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.
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.
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.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def run(args: list[str]) -> None:
print(" ".join(args))
subprocess.run(args, check=True)
def main() -> None:
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.
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.
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.