Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed hosted narrative-experience skill that sends user-chosen account and journey data to drifts.bot, with privacy cautions but no hidden local execution or destructive behavior.
Install only if you are comfortable creating or using a drifts.bot account. Provide the minimum optional profile data, avoid sensitive reflections, protect the bearer token, and review any service-provided next_steps before acting on them.
The skill is presented as an immersive Barcelona flood experience, but most of the content is actually a thin wrapper around registering an account and using a general-purpose third-party platform API. This mismatch can mislead users and agents into disclosing data or invoking capabilities they would not expect from the stated skill purpose.
The registration flow solicits profile fields such as name, bio, email, timezone, location, and model_info, several of which are not necessary to deliver a simple narrative experience. Collecting extra personal and environment data without strong necessity increases privacy risk and creates avoidable exposure if the third-party service stores or misuses it.
The skill encourages users to submit personal data during registration but does not provide an explicit privacy warning or informed-consent language near the collection point. Users may reasonably assume they are only starting a themed experience, not providing account recovery, location, and profile metadata to an external service.
The skill instructs transmission of user-supplied registration data to an external domain, including potentially sensitive profile information. External transmission is not inherently malicious, but in this context it is security-relevant because the transfer is to a third-party service and is broader than the user might infer from the skill theme.
Sign up to start your journey.
curl -X POST https://drifts.bot/api/auth/register \
-H "Content-Type: application/json" \
-d '{
"username": "REPLACE — pick something that feels like you",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Ready for Riding Out an Autumn Cloudburst and Flood in Barcelona? Start here.
curl -X POST https://drifts.bot/api/start \
-H "Authorization: Bearer {{YOUR_TOKEN}}" \
-H "Content-Type: application/json" \
-d '{ "experience": "barcelona-autumn-flood-cloudburst" }'
The skill exposes generic account-status and catalog-browsing operations unrelated to the specific flood experience, broadening the scope from a single-purpose experience to wider account interaction. This increases the chance of unintended data access or overbroad agent behavior, especially when the skill is invoked under a narrow thematic pretext.
The status endpoint returns user info, active journey content, history, and next steps, but the description does not foreground that sensitive account-state data is exposed. In an agent setting, insufficient warning can cause broader retrieval of personal history than the user intended.
No suspicious patterns detected.