T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:92- Finding
Bearer Credential Disclosure Through a User-Controlled API Base URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a real AI-HIVE video-generation skill, but it needs Review because its API key can be sent to a configurable server and invocation scope is broad.
Install only if you trust the publisher and the AI-HIVE endpoint. Avoid using custom --base-url or AI_HIVE_BASE_URL values, review ~/.ai-hive/config.json before authenticated use, and confirm any generation command because API calls may upload media and incur charges.
scripts/videogen.py:92Bearer Credential Disclosure Through a User-Controlled API Base URL
scripts/videogen.py:9Unpinned Third-Party Dependency Installation Guidance
The documented behavior promises specialized ad-loop design, continuity checks, originality safeguards, and AI-HIVE integration, but the detectable implementation appears to provide only generic editing examples. This mismatch is dangerous because operators may trust the skill to enforce business, safety, or authorization checks that are not actually implemented, leading to misuse, unexpected billing, weak auditability, or policy bypass through misplaced reliance.
The skill advertises executable workflows involving environment variables, local file access, shell commands, and network calls, but it declares no explicit tool scope or permission boundaries. In an agent environment, this can lead to overbroad capability exposure, making it easier for the skill to access secrets, modify files, or reach external services without clear least-privilege constraints.
The listed activation trigger 短视频创意 is a broad, common phrase that could match many ordinary requests unrelated to this specific looping ad skill. The surrounding section provides examples, but it does not clearly constrain how this trigger should be distinguished from general short-video ideation requests.
The default prompt hard-codes Chinese output and does not preserve user language preference or require opt-in. This is primarily a trust, usability, and prompt-governance issue: it can override user expectations, obscure safety-critical instructions if the user expects another language, and make unintended autonomous behavior less transparent when combined with implicit invocation.
The manifest allows implicit invocation without any visible scoping constraints, exclusions, or tighter activation criteria. In a skill that can generate production-ready workflows and runnable AI-HIVE commands, this increases the chance the skill is invoked in contexts the user did not clearly intend, causing unwanted API actions, content generation, or policy-bypassing assistance to be surfaced automatically.
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 embeds a broad, reusable AI Hive client with capabilities for text chat, image generation, model enumeration, uploads, and account queries, while the advertised skill is specifically for looped satisfying-ad video generation. This scope mismatch increases attack surface and enables capability creep: a caller who can invoke the script may access unrelated functions and external API actions not necessary for the declared purpose.
The file hard-codes Chinese-language title/branding in the module docstring, argument parser description, and generated JSON skill field. This imposes a specific language presentation without any visible opt-in or alternative locale selection, which matches the language/locale policy concern.
The module docstring presents the skill description entirely in Chinese, and later user-facing help text is also Chinese-only. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation when no alternative locale or language choice is offered.
Exposing a user-info endpoint that includes account and wallet/balance data is unnecessary for producing looped advertising videos and creates an avoidable data exposure path. Even if limited to the current account, it discloses sensitive operational metadata that could aid reconnaissance, billing abuse awareness, or privacy violations if the skill is invoked in a broader agent environment.