Back to skill
Skillv1.0.2
ClawScan security
whoami · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousMar 3, 2026, 4:12 PM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's code and instructions match a remote profile-sync purpose, but there are notable inconsistencies and privacy/metadata gaps you should review before installing.
- Guidance
- Before installing or enabling this skill, consider: 1) The skill stores and uploads a personal profile to a remote service (default https://whoamiagent.com). Only use it if you trust that service and its privacy policy. 2) The skill requires an API key saved to ~/.whoamiagent (WHOAMI_API_KEY), but the registry metadata did not declare this credential — verify where that config comes from and inspect it before running. 3) The SKILL.md instructs using curl to download a one-time config URL and save it directly to your home config file; do not run those commands if you cannot verify the URL/source. 4) Environment variables (WHOAMI_ENDPOINT, WHOAMI_FRONTEND_URL) can redirect the skill to arbitrary endpoints — ensure these are unset or point to trusted hosts. 5) Avoid putting secrets or very sensitive personal data in the profile; the skill will POST profile content to a third-party API. 6) If you still want to try it, run the script in a controlled environment first (inspect ~/.whoamiagent after setup, test against a non-production endpoint, or sandbox it). If you want a safer alternative, request the skill author to add explicit registry metadata listing the required API key and to include an option to preview/validate any downloaded config before writing it to disk.
Review Dimensions
- Purpose & Capability
- okThe name/description (user identity profile sync) align with the included script and SKILL.md: the skill reads/writes a Markdown profile to a remote service and stores a local config at ~/.whoamiagent. No unrelated binaries or credentials are requested in the files.
- Instruction Scope
- noteSKILL.md and the script instruct the agent to auto-open a browser for login and to curl a user-provided one-time configuration URL and save its contents directly to ~/.whoamiagent. The agent is instructed to upload profile content to the remote API (POST /api/profile). These behaviors are coherent with the stated purpose but carry privacy risk: user profile data (potentially sensitive) will be transmitted to an external service, and the agent is told to write a config file fetched from an external URL without local validation.
- Install Mechanism
- okNo install spec and no external binary downloads — the skill is instruction+script only. Execution uses the system python3 interpreter, which is proportionate to the task.
- Credentials
- concernThe runtime requires an API key stored in ~/.whoamiagent (WHOAMI_API_KEY), but the registry metadata lists no primary credential or required env vars — a mismatch. The script also respects WHOAMI_ENDPOINT and WHOAMI_FRONTEND_URL environment variables (which can redirect traffic to arbitrary hosts), but these are not declared in metadata. The skill will transmit user profile content to an external endpoint, so requiring and documenting the API credential in the registry would be expected but is missing.
- Persistence & Privilege
- okThe skill does not request always:true or other elevated platform privileges. It writes/reads a config file in the user's home (~/.whoamiagent) and may delete temp files created during updates; this behavior is consistent with its functionality.