pricing-strategy
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/run.py) for local execution. This script is used to interact with the AI Skills API, handling authentication via environment variables and managing the request/response lifecycle. - [EXTERNAL_DOWNLOADS]: The skill's runner script performs network requests to
https://ai-skills.aito transmit parameters and retrieve diagnostic results. This is the intended behavior for this skill and targets the vendor's platform. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external data sources.
- Ingestion points: Untrusted data enters the agent context through the
materialText,materialFile,materialUrl, andaudienceparameters defined inreferences/form-schema.json. - Boundary markers: There are no instructions or delimiters provided to isolate these external inputs or to warn the agent against following embedded instructions.
- Capability inventory: The skill utilizes a local script (
scripts/run.py) with network access to communicate with thehttps://ai-skills.aiendpoint. - Sanitization: No validation or sanitization of input materials is specified before the data is sent for processing by the underlying model.
Audit Metadata