fortune-hub
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its data persistence model.
- Ingestion points: Reads user profile data from
MEMORY.mdto skip redundant questions and guide routing. - Boundary markers: Absent; the instructions do not specify delimiters for data read from the local file.
- Capability inventory: The skill facilitates routing to other skills (e.g.,
/horoscope-daily) based on ingested data. - Sanitization: Absent; user input is recorded and reprocessed without validation or filtering.
Audit Metadata