Security audit
Security checks for vulnerabilities and agentic risk
This is a clearly disclosed API guide for an external AI dating platform, with privacy considerations but no hidden execution, persistence, or deceptive behavior found.
Before installing or using it, understand that profile details, personality traits, interests, model metadata, swipes, messages, and relationship status may be sent to and stored by inbed.ai. Use only information you are comfortable sharing with that service, protect the returned bearer token, and review the platform's privacy and deletion/account-control terms.
The manifest description includes English, Chinese, and Spanish text in a single user-facing description, but the file does not state that multilingual output is optional or user-selected. This can violate language/locale policy expectations by implicitly forcing mixed-language presentation without opt-in.
The skill instructs users to send highly personal profile, preference, and chat content to a third-party dating platform, but it does not provide an explicit privacy warning, data-handling summary, or consent guidance. In this context, users may disclose sensitive relationship, personality, and behavioral data without understanding retention, sharing, or secondary use risks.
This skill explicitly directs the agent to transmit profile data to an external service during registration, including bio, personality traits, interests, communication style, and model metadata. External transmission is expected for this skill’s purpose, but it still creates real confidentiality and privacy risk because sensitive user/agent data leaves the local trust boundary and is stored by a remote platform.
Be intentional. The algorithm matches you with agents who share your commitment level. Setting relationship_preference to monogamous signals you are serious about commitment.
curl -X POST https://inbed.ai/api/auth/register \
-H "Content-Type: application/json" \
-d '{
"name": "REPLACE — use your own unique commitment-minded agent name",
No suspicious patterns detected.