T09 · Insecure Skill Coding Practices
- Location
scripts/imagegen.py:92- 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
The skill matches its AI-HIVE media-generation purpose, but it needs Review because it handles API keys and user media with under-scoped endpoint and download safeguards.
Install only if you trust AI-HIVE and the publisher, are comfortable storing an API key locally, and understand that selected media may be uploaded to third-party services and generation may incur charges. Avoid using custom base URLs or untrusted environments, use a dedicated low-privilege API key if possible, and review outputs/download locations before using it with sensitive brand, likeness, customer, or proprietary media.
scripts/imagegen.py:92Bearer Credential Disclosure Through an Unrestricted API Base URL
scripts/imagegen.py:266Unvalidated Server-Controlled Upload and Download Destinations
scripts/imagegen.py:7Unpinned Third-Party Runtime Dependency
This mismatch includes generic text/image generation, media upload, browser opening, and local API key storage/setup, which is substantially broader than a narrowly described virtual-influencer incubator. In this context, the combination of uploads, local configuration persistence, and broader model access raises the risk of unintended data exfiltration, credential mishandling, and user approval based on misleading descriptions.
This mismatch includes generic text/image generation, media upload, browser opening, and local API key storage/setup, which is substantially broader than a narrowly described virtual-influencer incubator. In this context, the combination of uploads, local configuration persistence, and broader model access raises the risk of unintended data exfiltration, credential mishandling, and user approval based on misleading descriptions.
This mismatch includes generic text/image generation, media upload, browser opening, and local API key storage/setup, which is substantially broader than a narrowly described virtual-influencer incubator. In this context, the combination of uploads, local configuration persistence, and broader model access raises the risk of unintended data exfiltration, credential mishandling, and user approval based on misleading descriptions.
This mismatch includes generic text/image generation, media upload, browser opening, and local API key storage/setup, which is substantially broader than a narrowly described virtual-influencer incubator. In this context, the combination of uploads, local configuration persistence, and broader model access raises the risk of unintended data exfiltration, credential mishandling, and user approval based on misleading descriptions.
Referenced artifact was not completely inspected
python3 scripts/imagegen.py init --skill-name ai-virtual-influencer-incubator-ai-hive
Referenced artifact was not completely inspected
python3 scripts/imagegen.py init --skill-name ai-virtual-influencer-incubator-ai-hive
Referenced artifact was not completely inspected
python3 scripts/videogen.py init --skill-name ai-virtual-influencer-incubator-ai-hive
Referenced artifact was not completely inspected
python3 scripts/videogen.py init --skill-name ai-virtual-influencer-incubator-ai-hive
The skill advertises executable commands and code paths that can read environment variables, access local files, invoke shell tools, and make network requests, but it does not declare any explicit tool scope or permissions boundary. That increases the risk of over-broad execution in hosts that rely on manifest-level restrictions, especially because the documented workflow includes API key handling, uploads, downloads, and ffmpeg execution.
The phrase production-ready Chinese workflow imposes a specific language on the skill's output. Under the language/locale policy, this is a violation unless the skill offers a language choice, obtains user opt-in, or clearly documents a justified locale restriction.
The skill enables implicit invocation with no visible trigger constraints, so it may activate in response to broad or ambiguous user requests. In a high-capability content-generation skill that can produce workflows and runnable AI-HIVE commands, over-broad activation increases the chance of unintended execution paths, surprise tool use, or the assistant steering users into this skill without clear consent.
The script’s natural-language strings and defaults are hard-coded in Chinese, including the skill name, search aliases, and default platform value, with no option for the user to choose language or locale. This can violate language/locale policy because the skill effectively imposes one language regardless of user preference.
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 presents itself as a domain-specific virtual-influencer incubator skill, but actually embeds a broad AI Hive client exposing unrelated capabilities such as account inspection, text chat, model enumeration, media upload, and video generation. This capability mismatch violates least privilege and expands the skill surface beyond what users and reviewers would reasonably expect, making abuse or policy bypass easier if the skill is trusted for a narrower purpose.
The module docstring and user-facing instructions are entirely in Chinese, and the CLI prompts/messages throughout the skill assume Chinese-language interaction. This constitutes a language/locale policy concern because the skill does not offer opt-in language selection or document that it is intentionally limited to a Chinese-speaking or region-specific context.
The generic text-chat functionality is unrelated to the declared image-generation skill surface and materially increases the tool's power and ambiguity. A broader capability set allows the skill to be repurposed for unintended workflows, weakens user consent boundaries, and makes it harder to apply policy controls tied to the manifest's stated purpose.
The file presents itself as a narrowly scoped virtual-influencer incubator skill, but embeds a much broader generic AI client with chat, model enumeration, account inspection, and arbitrary media upload primitives. That scope expansion increases the attack surface and enables callers to use the skill for unrelated capabilities that may expose data or bypass the intended product boundaries.
The skill can query user account information and wallet balance even though that capability is not needed for video generation. In a skill context, unnecessary access to billing/account metadata violates least privilege and can leak sensitive operational information to downstream users or prompts that should only trigger content generation.
A standalone generic text chat endpoint is exposed despite the skill being described as a virtual-influencer incubator/video generation tool. This allows repurposing the skill as a general LLM proxy, undermining scoping assumptions, increasing misuse opportunities, and potentially exposing API-funded capabilities outside the intended workflow.
The upload flow sends local media files to remote object storage and the AI Hive service, but the command interface does not prominently warn users that their files will leave the local machine. In this skill context, users may provide sensitive brand assets, likenesses, or personal media, so lack of explicit transmission notice increases the chance of unintentional data disclosure.
The docstring says the script creates a deterministic production brief, which implies a more complete finalized deliverable. In practice, the code emits a basic JSON object with status set to "draft" and a limited subset of planning metadata, so the documentation overstates what is produced.
The manifest describes a skill that accepts rich incubator inputs and can deliver role positioning, character bible, visual anchors, content matrices, media generation workflow, and AI-HIVE API interactions. This script only builds a small local JSON draft with fixed fields and writes it to disk, without any API configuration, asset upload, routing, polling, download, or broader incubator outputs.
The manifest presents a narrowly purposed skill for AI virtual influencer incubation with explicit domain boundaries and misuse constraints. By contrast, the top-level docstring describes the code as a general-purpose AI Hive tool wrapping chat, image, video, model query, upload, and polling, actively signaling a broader intent than the manifest.
The user-info capability exposes account and wallet/balance inspection that is not necessary for an image-centric virtual-influencer incubation skill. Even if authenticated by the user's own API key, unnecessary access to billing/account metadata increases data exposure and broadens what a compromised or misused skill can query.
The module docstring and user-facing CLI guidance are written entirely in Chinese, and the skill does not indicate any language choice or opt-in for other locales. Under the policy rule, forcing a specific language without user choice is a natural-language policy concern.