MindStudio To API Custom Function Skill

AdvisoryAudited by Static analysis on May 10, 2026.

Overview

Detected: suspicious.exposed_secret_literal

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

A generated function could create, update, or retrieve data from an external service depending on the API endpoint and method the user chooses.

Why it was flagged

The skill generates code that can call user-specified external endpoints with different HTTP methods. This is central to the purpose, but users should confirm the method and endpoint are safe before running generated code.

Skill content

API endpoint — the full URL to call ... HTTP method — GET, POST, etc. ... Use `await fetch(...)` for HTTP calls

Recommendation

Review the generated URL, HTTP method, headers, request body, and error handling before pasting it into MindStudio, especially for payment, CRM, production, or delete/update endpoints.

NoteHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

The generated function will be able to act with whatever permissions are attached to the API key or token the user provides.

Why it was flagged

The skill expects API credentials for the user-selected provider, but it explicitly directs generated configs to use MindStudio secret fields rather than plain text.

Skill content

Authentication — API key header name, Bearer token, Basic auth, OAuth, or none ... Use `"secret"` type for API keys — never `"text"`

Recommendation

Use scoped, least-privilege API keys when possible, avoid production admin tokens for testing, and revoke keys that are no longer needed.

NoteHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

Workflow data may be transmitted to the selected API provider, and returned data may remain available in MindStudio workflow variables.

Why it was flagged

The template sends workflow inputs to an external API and stores the API response, including a raw JSON output, into workflow variables.

Skill content

body: JSON.stringify({ field: inputVal, option: optional }) ... ai.vars[ai.config.outputRaw]   = JSON.stringify(data);

Recommendation

Only send data appropriate for the chosen provider, check provider privacy requirements, and avoid storing full raw responses if they may contain sensitive information.

Findings (2)

critical

suspicious.exposed_secret_literal

Location: EXAMPLES.md:14
Finding: File appears to expose a hardcoded API secret or token.

critical

suspicious.exposed_secret_literal

Location: SKILL.md:52
Finding: File appears to expose a hardcoded API secret or token.