Instruqt
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill is a coherent Instruqt integration, but it gives broad authenticated API/proxy control, including mutating and DELETE requests, without clear approval or scope limits.
Review this skill before use. It appears purpose-aligned for Instruqt, but connect only the intended account, verify the Membrane CLI install source, and require explicit approval before any direct proxy request or action that creates, updates, or deletes Instruqt data.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
An agent using this skill could make broad changes to Instruqt resources if prompted or if it chooses an unsafe proxy request.
This documents a broad authenticated API escape hatch, including write and delete methods, without clear user-approval, scoping, or rollback guidance.
When the available actions don't cover your use case, you can send requests directly to the Instruqt API through Membrane's proxy... HTTP method (GET, POST, PUT, PATCH, DELETE).
Require explicit user confirmation before POST, PUT, PATCH, or DELETE requests, prefer discovered scoped actions, and document safe limits for proxy use.
The skill can act through the connected Membrane/Instruqt account according to that account's permissions.
The skill relies on delegated authentication and automatic credential refresh. This is expected for an Instruqt integration, but it is sensitive account authority.
Membrane handles authentication and credentials refresh automatically
Use the least-privileged Instruqt account or tenant available and revoke the Membrane connection when it is no longer needed.
The installed CLI code is outside the reviewed skill artifact and may change over time as the latest package changes.
The skill asks the user to install a global npm CLI at the latest version. This is purpose-aligned, but unpinned external installs have normal supply-chain and provenance risk.
npm install -g @membranehq/cli@latest
Install from the official Membrane source, consider pinning a known version, and review the CLI package before use in sensitive environments.
Remote setup instructions could influence what the agent does next if treated as authoritative.
The skill allows provider-returned instructions to guide the agent during setup. This can be useful, but such instructions should not override the user's intent or safety checks.
`clientAction.agentInstructions` (optional) — instructions for the AI agent on how to proceed programmatically.
Treat returned agent instructions as untrusted guidance, summarize them to the user when they affect behavior, and keep user intent and approval requirements authoritative.