trading212-api
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard system utilities including
curlfor API requests,jqfor structured data parsing, andbcfor calculation of order costs and fund validation. - [EXTERNAL_DOWNLOADS]: Network operations are directed exclusively to official Trading 212 API domains (
live.trading212.com,demo.trading212.com) and vendor-controlled AWS S3 buckets for report downloads, which are considered safe vendor resources. - [INDIRECT_PROMPT_INJECTION]: The skill has an exposure surface for indirect prompt injection as it processes external data from the Trading 212 API.
- Ingestion points: The skill ingests JSON responses from multiple API endpoints (e.g., account summary, positions, and instrument metadata) via
curlinSKILL.md. - Boundary markers: The skill does not implement specific delimiters or instructions to treat ingested API data as untrusted.
- Capability inventory: The skill is capable of placing various order types (market, limit, stop) and cancelling orders via authenticated
curlrequests. - Sanitization: Data is parsed using
jq, which ensures structural integrity and filters raw API output before it reaches the agent context.
Audit Metadata