redis-expert
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting untrusted data through Redis keys and cache storage.
- Ingestion points: User-controlled 'id' and 'ip' variables used in Redis key construction in SKILL.md.
- Boundary markers: None present to distinguish untrusted input from command structure.
- Capability inventory: Redis read/write/delete operations (get, setEx, del, incr, expire) and Node.js session management in SKILL.md.
- Sanitization: Absent; input is interpolated directly into keys and data is parsed via JSON.parse without schema validation.
Audit Metadata