The Agent Skills Directory

[PROMPT_INJECTION]: Metadata inconsistency detected. The skill metadata and license claim authorship by "Redis, Inc.", which contradicts the provided author context "kilo-org". This deceptive metadata can lead to misplaced trust in the skill's instructions.
[PROMPT_INJECTION]: Vulnerability to indirect prompt injection through log processing.
Ingestion points: The skill reads and processes data from SLOWLOG GET and FT.PROFILE as seen in SKILL.md and references/commands.md.
Boundary markers: There are no instructions provided to the agent to treat the output of these commands as untrusted data or to use delimiters.
Capability inventory: The agent is instructed to execute Redis diagnostic commands including INFO, CLIENT LIST, and MEMORY DOCTOR.
Sanitization: No sanitization or escaping mechanisms are implemented for the external data ingested from Redis.

redis-observability