Minimax Usage

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

ConcernHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

The skill may read credentials from a different, broader .env file than the user expects, such as a shared OpenClaw or project-level config file.

Why it was flagged

The script loads account credentials from a .env file two directories above the script, while the user-facing setup text says the .env should be in the same directory and the registry metadata declares no required env vars or primary credential.

Skill content

source "$(dirname "$0")/../../.env"

API_KEY="${MINIMAX_CODING_API_KEY}"
GROUP_ID="${MINIMAX_GROUP_ID}"

Recommendation

Before use, verify the exact .env path. Prefer changing the script to read a clearly scoped same-directory config file and declare MINIMAX_CODING_API_KEY and MINIMAX_GROUP_ID in metadata.

ConcernMedium Confidence

ASI05: Unexpected Code Execution

What this means

If that parent .env file contains shell commands or has been modified unexpectedly, running the usage check could execute those commands locally.

Why it was flagged

Using shell source executes the contents of the referenced .env file rather than only parsing key/value pairs, and the referenced file is outside the documented same-directory location.

Skill content

source "$(dirname "$0")/../../.env"

Recommendation

Use a safer parser for only the two needed variables, or source only a trusted, skill-local .env file after user review.