T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:89- 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 is mostly aligned with Amazon product video generation, but review is warranted because its API token can be sent to a configurable server and generated downloads can overwrite files if task metadata is malicious.
Install only if you trust AI Hive and the environment where this runs. Use a dedicated low-privilege API key, do not set custom base URLs unless you control them, run it in an isolated virtual environment, and avoid processing task IDs or API responses from untrusted servers until filename and origin validation are fixed.
scripts/videogen.py:89API Credential Disclosure Through an Unrestricted Base URL
scripts/videogen.py:399Path Traversal and Arbitrary File Overwrite in Generated-Media Downloads
SKILL.md:79Unpinned Third-Party Dependency Installation
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
--prompt 'Amazon product setup video based only on the merchant-approved instructions: lay out the supplied parts, show step 1, step 2 and step 3 in order with clear hand placement, then show the correctly assembled result. Do not skip safety steps, invent a component or display unprovided measurements.'
The skill invokes local scripts and documents capabilities that imply shell, file, environment, and network access, but it does not declare any explicit tool scope or permission boundaries. This increases the risk of overbroad execution in an agent environment, making it easier for a caller or downstream prompt to use the skill with more privileges than intended.
The file advertises and exposes a broad, general-purpose AI Hive client with text chat, image generation, model enumeration, media upload, and task polling, while the declared skill scope is Amazon ecommerce video generation/editing. This scope drift increases attack surface and permits capability abuse outside the reviewed intent, which can lead to unauthorized or unexpected use of the skill in agent environments that rely on manifest-level least privilege assumptions.
Text chat and image-generation features materially exceed the stated purpose of an Amazon product video editing/generation skill. In agent ecosystems, these hidden extra capabilities can bypass user and platform expectations, enabling prompt misuse, unreviewed content generation paths, and broader data exfiltration or policy evasion opportunities than the skill description suggests.
This markdown file contains user-facing natural language exclusively in Chinese across the substantive changelog entries. Under the policy rule for language/locale, this can be a violation when a skill forces a specific language without user opt-in or justification.
The description contains both English and Chinese terms, which indicates language-specific behavior or targeting. The file does not explicitly state that users can choose their preferred language or that this multilingual scope is limited to a justified locale-specific context.
The example API key placeholder uses Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. There is no indication that the skill is region-specific or that users may choose another language, so this appears to violate the language/locale policy.
This code file includes natural-language descriptions and instructions exclusively in Chinese in the module docstring. Under the policy, language constraints should not be forced without opt-in or a clearly documented justification, and no alternative language option is offered here.
The user-info endpoint exposes account metadata and wallet/balance information that is unrelated to Amazon video creation. In a skill context, this is an unnecessary sensitive-data access path that could be used for reconnaissance or privacy leakage if an agent or caller invokes it unexpectedly.