The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for managing the Redis service via systemctl, adjusting kernel parameters with sysctl, and performing database operations through redis-cli. These are legitimate administrative functions required for the skill's primary purpose.
[EXTERNAL_DOWNLOADS]: References provided in docs.md point to official Redis documentation (redis.io) and well-known community repositories on GitHub. These are considered trusted and safe sources.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection due to its ability to read data from an external Redis store.
Ingestion points: Data retrieval commands such as GET, HGETALL, SCAN, and BRPOP are listed in SKILL.md and references/common-patterns.md.
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions when processing data retrieved from Redis.
Capability inventory: The skill permits package installation, service restarts, and kernel-level configuration changes across various files.
Sanitization: No explicit logic for sanitizing or validating external data before it enters the agent's context is mentioned.

redis