The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill implements a long-term memory system which acts as an ingestion point for data that could potentially contain malicious instructions from previous interactions.
Ingestion points: The memory_recall tool and the autoRecall feature described in SKILL.md retrieve historical data and inject it into the prompt context.
Boundary markers: The documentation does not specify the use of delimiters or boundary markers to isolate retrieved memories from current instructions.
Capability inventory: The skill interacts with local openviking and openclaw services to manage state and configuration.
Sanitization: No explicit sanitization of retrieved memory content is mentioned in the tool definitions.
[COMMAND_EXECUTION]: The skill includes standard configuration and management commands for the openviking-server and openclaw CLI utilities.
[EXTERNAL_DOWNLOADS]: The documentation references a setup helper executed via npx, which is a standard procedure for configuring Node.js-based plugins in the specified environment.

openviking-memory