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 curl for API requests, jq for structured data parsing, and bc for 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 curl in SKILL.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 curl requests.
  • Sanitization: Data is parsed using jq, which ensures structural integrity and filters raw API output before it reaches the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:11 PM
Security Audit — agent-trust-hub — trading212-api