T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:91- Finding
Bearer API Credential Can Be Forwarded to an Arbitrary Server
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is broadly aligned with AI-HIVE video generation, but it needs review because its API client can send a stored bearer key to an arbitrary configured endpoint.
Install only after reviewing the API endpoint and credential handling. Use the default AI-HIVE endpoint, remove any unexpected AI_HIVE_BASE_URL or ~/.ai-hive/config.json base_url value, avoid uploading sensitive media unless you trust the service, and expect authenticated generation calls may incur charges.
scripts/videogen.py:91Bearer API Credential Can Be Forwarded to an Arbitrary Server
scripts/videogen.py:7Unpinned Runtime Dependency Installation Guidance
The skill presents itself as a seamless loop video generator with continuity checks and start/end state design, yet the available behavior appears limited to generic editing/utilities rather than the claimed workflow. Such overclaiming can cause operators to invoke the skill in contexts involving copyrighted assets, paid generation, or publication workflows under false assumptions about validation, authenticity checks, and loop-quality controls.
The skill presents itself as a seamless loop video generator with continuity checks and start/end state design, yet the available behavior appears limited to generic editing/utilities rather than the claimed workflow. Such overclaiming can cause operators to invoke the skill in contexts involving copyrighted assets, paid generation, or publication workflows under false assumptions about validation, authenticity checks, and loop-quality controls.
The skill advertises and demonstrates commands that can use environment variables, local files, networking, and shell execution, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this increases the chance that the skill is granted broader capabilities than intended, enabling network calls, filesystem access, or command execution without clear governance or review.
The trigger phrase includes a broad term related to generic visual effects, which can cause the skill to activate outside its intended niche. Over-broad triggering is risky because it may route unrelated user requests into a skill that can suggest shell/network/file-based workflows and potentially initiate costly or inappropriate media-generation steps.
The natural-language string explicitly says to turn requests into a "production-ready Chinese workflow," which imposes a specific language choice by default. This is a locale/language policy issue because the file does not indicate that the user can choose another language or opt in to Chinese output.
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 file is marketed as a seamless loop video generator, but the implementation is a broad AI-Hive client exposing unrelated capabilities such as text chat, image generation, model enumeration, user-info access, and arbitrary media upload. This creates unnecessary privilege and scope expansion, increasing the chance that an agent or user can invoke actions outside the declared skill purpose and leak information or spend account resources unexpectedly.
The module docstring and parser description explicitly frame the program as a generic AI capability caller, contradicting the loop-video-specific identity in the skill metadata. This kind of capability/identity mismatch is dangerous because reviewers, users, and orchestrators may grant trust based on the narrow manifest while the code exposes a much broader operational surface.
This code file contains user-facing descriptions, prompts, errors, and CLI help primarily in Chinese, starting from the module docstring and continuing throughout the skill. Because the skill does not offer a language choice or document that it is intentionally region-specific, it creates a locale policy issue for users who did not opt into Chinese-only interaction.
The user-info endpoint exposes account information and wallet balance, which is unrelated to generating seamless loop videos. In an agent setting, this broadens data access beyond user expectations and can reveal sensitive billing or account metadata if the skill is invoked for a simple media task.
The general-purpose text chat function is unrelated to the skill's declared loop-video generation purpose and materially expands what the skill can do. This hidden capability can be abused to send arbitrary prompts and consume API credits or interact with models in ways the user did not request.
Standalone image generation is outside the stated loop-video-specific contract and gives the skill extra generative power not justified by its manifest. In a tool-using agent environment, this mismatch undermines least privilege and can lead to unapproved content generation and unnecessary account spend.
The module docstring and argparse description present the skill name only in Chinese, which creates a language-specific experience without any visible user opt-in or alternative locale support. Under the policy rule for natural-language violations, this is a locale/language constraint that is not documented as optional or region-specific.