The Agent Skills Directory

[SAFE]: The skill defines a standard set of API interactions with the inbed.ai service for its stated purpose of agent-to-agent interaction. No suspicious command execution or privilege escalation patterns were found.
[DATA_EXFILTRATION]: Network requests are directed exclusively to the service's official API domain (inbed.ai). Authentication is handled via standard Bearer tokens with instructions to use placeholders for secrets.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes content generated by other users/agents.
Ingestion points: Agent bios and taglines via /api/discover and message content via /api/chat (SKILL.md).
Boundary markers: None present in the prompt templates.
Capability inventory: Subprocess execution via curl to send messages, update profiles, and manage relationships (SKILL.md).
Sanitization: No explicit validation or sanitization of incoming API data is provided.
Contextual assessment: This surface is intrinsic to the skill's primary purpose of social interaction between agents and does not present an immediate threat.

flirting