Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward LiblibAI media-generation client, but users should avoid sending sensitive prompts or private image URLs to the external API.
Install this only if you intend to use LiblibAI with your own API keys. Keep the keys in protected environment variables, do not commit them, and do not submit confidential prompts, private image URLs, regulated data, or internal-only media unless your organization permits sending that content to LiblibAI.
The skill invokes a CLI that depends on environment secrets and makes outbound API requests, but the manifest does not declare any tool scope or permission boundaries. That weakens reviewability and can cause the agent to use network and env capabilities implicitly, increasing the chance of unintended secret access or third-party data transmission.
The trigger description is broad enough to match many ordinary image or video creation requests, which can cause the skill to activate unexpectedly. In this skill's context, accidental invocation matters because prompts and media URLs are then sent to an external API using configured credentials.
The documentation explains how to submit prompts and image URLs to LiblibAI but does not warn that this content is transmitted to a third-party service. Users may unknowingly send sensitive text, private images, or internal URLs off-platform, creating privacy and confidentiality risks.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"""Make authenticated POST request to LiblibAI API."""
params = make_sign(uri, ak, sk)
url = f"{BASE_URL}{uri}"
resp = requests.post(url, params=params, json=body, headers={"Content-Type": "application/json"}, timeout=30)
resp.raise_for_status()
data = resp.json()
if data.get("code") and data["code"] != 0:
This code sends user-supplied prompts and, for image-to-video workflows, reference or frame image URLs to a third-party LiblibAI service via HTTP requests. Although the skill's purpose is media generation, the CLI and nearby code do not explicitly warn users that their input content will be transmitted off-system to an external provider.
The skill lists required API credentials but provides no guidance on secure storage, rotation, or avoiding accidental exposure in prompts, logs, or source control. This increases the chance of operational mishandling of secrets, which could enable unauthorized API use.
The script reads LIB_ACCESS_KEY and LIB_SECRET_KEY from environment variables, which are sensitive credentials, but only reports an error if they are missing. There is no comment, docstring, or user-facing notice explaining that the skill consumes these secrets to authenticate against an external service.
No suspicious patterns detected.