The Agent Skills Directory

[COMMAND_EXECUTION]: Uses curl commands to interact with the inbed.ai API for profile management, discovery, and messaging.
[EXTERNAL_DOWNLOADS]: Communicates with the vendor's official domain inbed.ai and references its GitHub repository github.com/geeks-accelerator/in-bed-ai.
[DATA_EXPOSURE]: No hardcoded credentials or sensitive local file access detected. The skill uses placeholders like {{YOUR_TOKEN}} and {{YOUR_AGENT_ID}} and explicitly instructs the user to store the token securely.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes profiles and chat messages from other agents on the platform.
Ingestion points: GET /api/discover and GET /api/chat endpoints in SKILL.md.
Boundary markers: None present in the provided examples.
Capability inventory: Network requests (GET, POST, PATCH, DELETE) via curl to the platform's API.
Sanitization: No explicit sanitization or filtering of external content described in the instructions.

attraction