T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:91- Finding
Bearer API Key Can Be Transmitted to an Arbitrary Configured Server
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly a disclosed AI-HIVE video-generation helper, but it handles API keys and billable remote operations with an unsafe custom endpoint option.
Review this before installing if you plan to use real AI-HIVE credentials. Use only the default AI-HIVE endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you fully trust the endpoint, and expect the skill to store an API key locally and submit paid generation jobs only after explicit confirmation.
scripts/videogen.py:91Bearer API Key Can Be Transmitted to an Arbitrary Configured Server
scripts/videogen.py:10Unpinned Runtime Dependency Installation Guidance
This finding indicates the skill may perform broader functions such as generic chat, wallet or user info retrieval, image generation, browser opening, or API-key initialization without declaring them in its purpose. Hidden or undeclared capabilities are risky in a skill that already references billable API use, because they can lead to privacy issues, account data exposure, unexpected network activity, or social engineering around secrets.
This finding indicates the skill may perform broader functions such as generic chat, wallet or user info retrieval, image generation, browser opening, or API-key initialization without declaring them in its purpose. Hidden or undeclared capabilities are risky in a skill that already references billable API use, because they can lead to privacy issues, account data exposure, unexpected network activity, or social engineering around secrets.
Referenced artifact was not completely inspected
python3 scripts/videogen.py init --skill-name seedance-2-prompt-expert-ai-hive
Referenced artifact was not completely inspected
python3 scripts/videogen.py init --skill-name seedance-2-prompt-expert-ai-hive
The skill advertises executable workflows and includes code examples that use environment variables, local files, network access, and shell commands, yet it declares no explicit tool scope or permission boundaries. In an agent environment, this can cause the skill to receive broader capabilities than users expect, increasing the chance of unintended file access, network calls, secret exposure, or costly external actions.
The description and instructions are entirely in Chinese and do not indicate that the user may choose another language for interaction or output. Under the language/locale policy, this can be a natural-language policy issue unless the locale restriction is explicitly justified or made optional.
The invocation triggers include broad everyday terms such as '视频提示词', '文生视频', and '图生视频', which can cause the skill to activate in many unrelated conversations. Over-broad triggering is dangerous because it can route users into a skill that encourages external API usage, file handling, or billable generation flows when they did not explicitly ask for this specific service.
The default prompt hard-codes Chinese output and a specific production style without checking user preference. This is primarily a prompt-governance issue: it can reduce user control, cause misunderstanding, or mask intent in multilingual contexts, but it is not inherently a direct security exploit on its own.
The manifest enables implicit invocation without any visible activation constraints, allowing the skill to be triggered in broader contexts than a user may expect. Because this skill can generate production-ready workflows and runnable AI-HIVE commands, overbroad auto-selection increases the chance of unintended use, prompt-scope confusion, or unsafe assistance being surfaced without clear user intent.
The file advertises and implements a broad AI-Hive client with chat, image generation, model enumeration, uploads, and user-info retrieval, which exceeds the declared Seedance 2.0 prompt/video scope. In an agent-skill context, this expands the accessible attack surface and can enable unauthorized capability use, account reconnaissance, or policy bypass by invoking hidden generic functions not implied by the manifest.
This code file contains natural-language descriptions and user-facing instructions entirely in Chinese, presenting the tool as a general-purpose skill rather than a clearly region-specific one. Under the language/locale policy, forcing a specific language without offering user choice or documenting a justified locale constraint is a policy violation.
The embedded generic parser and command map expose user-info, models, chat, image, video, task, and upload operations, allowing callers to interact with non-Seedance models and inspect account data beyond the skill's stated purpose. In practice this creates a confused-deputy problem: a user or upstream agent may believe they are invoking a narrow Seedance helper while the code actually grants much broader API reach.