v0.1.1

WHOOP Morning

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 4:51 AM.

Analysis

The skill’s WHOOP OAuth use fits its purpose, but the auth and report programs it asks you to run are not included in the reviewed files, so you should review it before using WHOOP credentials.

GuidanceReview or obtain the missing bin/whoop-auth and bin/whoop-morning source before running this skill. If you proceed, use a dedicated WHOOP OAuth authorization, keep the token files private, verify where the daily message is sent, and remove the cron job and revoke the token if you stop using it.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agentic Supply Chain Vulnerabilities

SeverityMediumConfidenceHighStatusConcern

SKILL.md; file manifest

Run: `/home/claw/clawd/skills/whoop-morning/bin/whoop-auth ...` and `/home/claw/clawd/skills/whoop-morning/bin/whoop-morning`; manifest lists only `SKILL.md` and `lib/tokens.js`.

The reviewed package does not include the central auth and report executables that the user is instructed to run, even though those executables would handle WHOOP OAuth credentials and health data.

User impactA user may be asked to run unreviewed or missing helper programs before giving the skill access to WHOOP account data.

RecommendationDo not run the referenced bin/whoop-auth or bin/whoop-morning commands until the package includes those files or provides a verifiable source/install specification for them.

Rogue Agents

SeverityLowConfidenceHighStatusNote

SKILL.md

Recommended: schedule with Gateway cron (daily, morning). The cron job should run `whoop-morning` and send its output as a message.

The skill recommends recurring scheduled execution. This is disclosed and aligned with a morning report, but it creates ongoing automated activity.

User impactThe skill may keep running daily and sending WHOOP-derived messages until the schedule is removed.

RecommendationConfirm the cron schedule and message destination, and remove the job when you no longer want daily reports.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusNote

SKILL.md

`WHOOP_CLIENT_ID`, `WHOOP_CLIENT_SECRET`, `WHOOP_REFRESH_TOKEN`; scopes: `offline read:recovery read:sleep read:cycles read:profile`

The skill requests OAuth credentials and read access to WHOOP health/profile data. This is expected for a WHOOP report, but it is sensitive account authority and the registry metadata did not declare a primary credential.

User impactThe skill can access personal WHOOP recovery, sleep, strain/cycle, and profile information using long-lived OAuth authorization.

RecommendationUse only the documented scopes, store secrets securely, and revoke the WHOOP token if you stop using the skill.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

lib/tokens.js

const CACHE_DIR = `${process.env.HOME || '/home/claw'}/.cache/whoop-morning`; ... fs.writeFileSync(TOKENS_PATH, JSON.stringify(tokens, null, 2) + '\n');

The included code persists token objects to a local cache file. Local token caching is normal for OAuth refresh flows, but the tokens are sensitive.

User impactAnyone with access to the local token cache may be able to reuse WHOOP authorization until the token is revoked or expires.

RecommendationKeep the cache directory private, prefer a secrets manager where available, and delete cached tokens when uninstalling.