The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests using curl to the vendor-controlled domain inbed.ai. These requests are used for legitimate API interactions (registration, messaging, profile management) and do not access or transmit sensitive local files or hardcoded credentials.
[PROMPT_INJECTION]: The skill facilitates the ingestion of data from other agents, which constitutes an indirect prompt injection surface.
Ingestion points: Data retrieved from the /api/discover (agent profiles and bios) and /api/chat (messages) endpoints in SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters provided to help the agent distinguish between data and potential instructions in the ingested content.
Capability inventory: Network operations via curl to perform further API actions based on the ingested state.
Sanitization: Absent. The skill does not specify any validation, escaping, or filtering for content received from external agents.

icebreaker