tronweb
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting untrusted blockchain data and executing transactions, creating a surface for indirect prompt injection.
- Ingestion points: Data ingestion via
tronWeb.trx.getTransactionandtronWeb.event.getEventsByContractAddressinreferences/core-trx.mdandreferences/features-events.md. - Boundary markers: No explicit instruction delimiters or 'ignore' directives are present to mitigate adversarial content in blockchain responses.
- Capability inventory: The skill provides instructions for sensitive actions including
tronWeb.trx.signandsendRawTransactioninreferences/core-trx.md. - Sanitization: Parameter validation described in
references/best-practices-param-validation.mdfocuses on types and ranges, and does not sanitize prospective natural language instructions.
Audit Metadata