The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display SNMP trap data received from external network devices. This represents an indirect prompt injection surface where malicious data within trap fields could potentially influence the agent.
Ingestion points: Network traffic received via UDP on configurable ports.
Boundary markers: None specified in the instructions.
Capability inventory: Tools allow for starting/stopping the receiver and querying/viewing trap data (snmptrap_query, snmptrap_get_trap).
Sanitization: Not explicitly described.
[COMMAND_EXECUTION]: The skill facilitates the management of a background SNMP receiver process via tool calls (snmptrap_start_receiver, snmptrap_stop_receiver). These tools interact with the snmptrap-mcp server to perform network-level operations.

snmptrap-receiver