The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using curl to interact with peer bot APIs and a local fleet management service located at http://localhost:4000/api/fleet.- [DATA_EXFILTRATION]: The skill enables the transmission of conversation data and session keys to external network endpoints (http://<peer-url>/chat). This behavior allows the agent to send prompt context over the network during collaboration tasks.- [PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection (Category 8).
Ingestion points: The agent ingests untrusted data from group chat history (labeled with [username]) and peer bot metadata (labeled with [Peers: ...]).
Boundary markers: There are no explicit delimiters or boundary markers used to separate untrusted user or peer content from the skill's operational logic.
Capability inventory: The agent has the capability to perform network requests and process information across different domains using curl.
Sanitization: There is no logic provided to sanitize or validate the content of the conversation history or peer responses before they are used to influence the agent's behavior or network calls.

multi-bot