Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a straightforward Media.io image-transformation API wrapper, with normal third-party/API-key privacy risks and a fixable input-validation weakness but no hidden persistence or destructive behavior.
Install only if you are comfortable sending your Media.io API key, prompts, image URLs, and generated task identifiers to Media.io. Avoid private or regulated images unless your Media.io account and policies allow that use. Prefer an isolated Python environment, pin dependencies, and validate or encode task IDs before using the task-result helper broadly.
scripts/skill_router.py:55Unsanitized Path Parameter Allows Authenticated Same-Origin Endpoint Manipulation
SKILL.md:68Unpinned Third-Party Dependency Produces a Non-Reproducible Installation
The skill documents code paths that use environment variables, read local files under scripts/, and make outbound network requests, but it does not declare an explicit tool/permission scope. This weakens least-privilege controls and reduces transparency for reviewers and users about what capabilities the skill requires, which can enable over-broad execution in agent environments.
The skill takes user-provided prompts and image URLs and sends them to a third-party service, but the description does not clearly disclose that this data leaves the local agent environment. Users may unknowingly transmit sensitive images, internal URLs, or confidential prompt content to Media.io, creating privacy, compliance, and data-exposure risks.
The manifest says this skill transforms existing images using AI models, but this file documents an additional capability to query account credits. Account/billing introspection is not part of image transformation itself and expands the skill beyond its stated purpose.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"description": "API to query user credits balance.",
"api_header": "{\"list\": [{\"name\": \"X-API-KEY\", \"value\": \"API key to authorize requests\"}, {\"name\": \"Content-Type\", \"value\": \"application/json\"}], \"title\": \"Authorizations\", \"describe\": \"Add the following authorization information in the request header\"}",
"api_body": "{\"title\": \"Request Body\", \"category\": [{\"list\": [], \"title\": \"Query Credits\", \"describe\": \"Request body to query user credits balance\"}]}",
"api_request_demo": "{\"title\": \"Example Request\", \"request\": [{\"title\": \"Query User Credits\", \"language\": \"cURL\", \"code_example\": \"curl --request POST \\\\n --url https://openapi.media.io/user/credits \\\\n --header 'Content-Type: application/json' \\\\n --header 'X-API-KEY: <api-key>' \\\\n --data '{}'\"}]}",
"api_response": "{\"list\": [{\"name\": \"code\", \"type\": \"integer\", \"describe\": \"Response status code, 0 indicates success\"}, {\"name\": \"msg\", \"type\": \"string\", \"describe\": \"Response message, empty string on success\"}, {\"name\": \"data\", \"type\": \"object\", \"describe\": \"Response data object\"}, {\"name\": \"credits\", \"type\": \"integer\", \"describe\": \"User credits balance, located within the data object\"}], \"title\": \"Response\", \"describe\": \"After the request is successfully processed, the server will return the following response\"}",
"api_code_demo": "{\"list\": [{\"code\": \"0\", \"describe\": \"Success\"}, {\"code\": \"40001\", \"describe\": \"Invalid API key\"}, {\"code\": \"40002\", \"describe\": \"API key expired\"}], \"title\": \"Status Code\"}",
"content": null,
The documentation instructs clients to send user-provided image URLs and prompts to an external Media.io endpoint, but it provides no disclosure about third-party transmission, retention, or processing of potentially sensitive content. Users may unknowingly submit private images or confidential text prompts to an external service, creating privacy and compliance risk.
The manifest focuses on transforming images with AI models, while this file also exposes a separate task-status/result retrieval endpoint. Although related to async generation workflows, it is a broader job-management capability not described in the manifest text.
The file documents POST requests to external Media.io endpoints authenticated with an API key, but it does not disclose to users that query details and identifiers are transmitted off-system. For markdown/manifest-style skill documentation, omission of such privacy or system-impact warnings can leave users unaware of external data sharing.
No suspicious patterns detected.