israeli-agritech-advisor
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process data from external agritech APIs, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through API client methods such as
get_soil_readings,get_detections, andget_sitesdefined inSKILL.mdandSKILL_HE.md. - Boundary markers: Absent; the provided code snippets do not implement specific delimiters or instructions to ignore potential commands embedded in the external API responses.
- Capability inventory: Across
SKILL.mdandSKILL_HE.md, the skill utilizes Python (Bash(python:*)) for data processing and supports network operations (Bash(curl:*)) to interact with external agritech platforms. - Sanitization: Absent; there is no evidence of sanitization or strict schema validation for the JSON payloads returned by the third-party services before the data is processed by the agent.
Audit Metadata