T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:93- Finding
API Credential Disclosure Through an Unrestricted Base URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill fits its AI video workflow purpose, but it handles API keys, media uploads/downloads, and local file writes with weak controls that users should review before installing.
Review before installing. Use only the default AI-HIVE endpoint unless you fully trust a custom endpoint, prefer a limited or test API key, do not upload sensitive media unless you trust the service, choose a dedicated output folder, and confirm parameters before any billable generation. Be aware that local ffmpeg edits and downloads can overwrite files if paths collide.
scripts/videogen.py:93API Credential Disclosure Through an Unrestricted Base URL
scripts/videogen.py:278Untrusted Server-Controlled Upload and Download Destinations
scripts/videogen.py:389Path Traversal and Unintended File Overwrite Through Server-Controlled Filename Components
scripts/edit_video.py:59Forced Overwrite in Local Video Editing Operations
The skill description promises a high-level AI directing and AI-HIVE integration workflow, but the detected behavior does not implement those capabilities and instead appears centered on lower-level local video handling. This mismatch is dangerous because users or supervising agents may authorize the skill under false assumptions, leading to unsafe trust decisions, unintended file operations, or hidden capability creep outside the stated purpose.
The skill advertises executable workflows involving environment variables, filesystem access, networking, and shell commands but does not declare any explicit tool scope or permissions boundary. In an agent environment, this can lead to overbroad runtime authority, making it easier for the skill to access sensitive data, modify local files, or invoke external services without clear review or restriction.
The manifest description and title are written as Chinese-only skill framing for invocation and use, and the usage section later treats language as an input parameter rather than offering a user-facing choice for the skill's own responses. This can violate language/locale policy when a skill implicitly forces a specific language without explicit opt-in or documented regional justification.
The manifest's default_prompt explicitly requires a "production-ready Chinese workflow," which imposes a specific language choice regardless of the user's preference. This is a natural-language locale policy issue because the file does not offer an opt-in or alternative language selection.
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 skill focused on producing reviewable directing plans and, when generation is needed, interacting with AI-HIVE OpenAPI for configuration lookup, upload, pricing, routing, polling, and download. This script instead performs direct local media transformations with ffmpeg (trim, aspect conversion, mute, loudness normalization, concat), which is a separate video-editing capability not described as part of the skill's purpose.
The file is presented as a Seedance video-director skill, but it exposes a broad, general-purpose AI Hive client with chat, image, video, model listing, upload, and account-related capabilities. This capability overreach violates least privilege and increases the attack surface: an agent invoking this skill could perform actions unrelated to the declared purpose, including arbitrary model access and media handling.
The skill includes a user-info endpoint that can retrieve account information and wallet balance, which is unrelated to generating Seedance directing outputs. In a broader agent environment, unnecessary access to billing/account metadata increases privacy exposure and can aid reconnaissance about the user's subscription state or available funds.
The manifest promises a safety/cost-control workflow of producing a reviewable directing plan before expensive generation, but the implementation directly submits generation requests with no review gate, confirmation step, or policy enforcement. In an agent setting, this can lead to unintended costly actions or bypass of human review expectations embedded in the skill description.
This code file contains natural-language descriptions and CLI guidance entirely in Chinese, including the module docstring and most user-facing output. Because the skill does not offer a language/locale choice or document that it is intentionally region-specific, it may violate a language/locale policy requiring user opt-in.