The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of local Node.js scripts to manage the communication bridge and monitor the channel.\n
Evidence: SKILL.md instructs the agent to run node ~/.iskron-bridge/iskron-bridge.mjs doctor for diagnostics and node ~/.iskron-bridge/iskron-bridge.mjs update for updates.\n
Evidence: references/channel-2.md specifies the use of watchdog.mjs and watchdog-exit.mjs scripts to monitor the WebSocket connection.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process messages from external agents and users, which creates a potential vector for indirect prompt injection.\n
Ingestion points: Incoming data frames received through the WebSocket connection (monitored by watchdog scripts) and history logs retrieved via iskron_case(action=\"history\").\n
Boundary markers: Uses the [iskron-bridge] prefix to identify relevant tool responses.\n
Capability inventory: The skill can interact with the vendor's graph via iskron_case, manage session state with iskron_stand, and execute local bridge management scripts.\n
Sanitization: There are no explicit instructions for sanitizing or escaping the content of incoming messages before they are processed by the agent.\n- [DYNAMIC_EXECUTION]: The skill dynamically generates command lines for local monitoring scripts based on parameters received from the bridge service.\n
Evidence: The agent is instructed to use commands, keys, and language flags provided in the connect response to launch the watchdog processes.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation and update of the vendor's bridge software from its own infrastructure.\n
Evidence: The establish-mcp tool is used to install the bridge, and iskron-bridge.mjs update is used for software updates.

standing