T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:91- Finding
AI-HIVE API Key Can Be Forwarded to an Arbitrary Endpoint
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/videogen.py:91AI-HIVE API Key Can Be Forwarded to an Arbitrary Endpoint
scripts/videogen.py:267Unvalidated Server-Controlled URLs Enable Media Diversion and Client-Side Request Forgery
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.
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.
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.
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.
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.
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:
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.
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.