Wisetime
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This appears to be a legitimate WiseTime integration, but the provided instructions give broad authenticated API access that could change or delete time-tracking/business records without clear approval limits.
Install only if you trust Membrane and the npm CLI. Use a least-privilege WiseTime account, ask the agent to show intended actions first, and require explicit approval before any write, delete, or raw proxy request. Revoke the Membrane/WiseTime connection when it is no longer needed.
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 potentially create, update, or delete WiseTime records such as time entries or business/project data if it chooses or is instructed to use the proxy path.
This documents a raw authenticated API escape hatch, including mutating and deleting methods, without visible guardrails or confirmation requirements in the provided artifact.
When the available actions don't cover your use case, you can send requests directly to the WiseTime API through Membrane's proxy ... `-X, --method` | HTTP method (GET, POST, PUT, PATCH, DELETE).
Prefer scoped Membrane actions, require explicit user confirmation before POST/PUT/PATCH/DELETE or proxy requests, and use a least-privilege WiseTime account.
The agent may be able to access or modify anything the connected WiseTime/Membrane account is allowed to access.
The skill relies on delegated Membrane/WiseTime authentication and token refresh. This is expected for the integration, but it means actions run with the connected account's privileges.
Membrane handles authentication and credentials refresh automatically ... `membrane login --tenant --clientName=<agentType>`
Connect only an account with appropriate permissions, review requested actions, and revoke the connection when it is no longer needed.
Installing a global, unpinned CLI gives that package local execution capability and may install a newer version than the one reviewed.
The setup uses a global npm install pinned to `latest`, so the exact CLI code can change over time. It is user-directed and central to the skill's purpose, but users should verify the package source.
npm install -g @membranehq/cli@latest
Install only from the official npm package, consider pinning a known version, and avoid running the setup in highly sensitive environments without review.
WiseTime request details and returned data may pass through Membrane while the integration is used.
WiseTime API requests and authentication are routed through Membrane as a gateway. This is disclosed and purpose-aligned, but it is an external data boundary users should understand.
send requests directly to the WiseTime API through Membrane's proxy ... injects the correct authentication headers
Use this only if you trust Membrane for the relevant WiseTime data, and avoid sending unnecessary sensitive content through proxy requests.