moralis-data-api
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external blockchain APIs (EVM, Solana, Bitcoin) which are attacker-controllable (anyone can write to the blockchain).
- Ingestion points: API response data is parsed by the agent as seen in files like
rules/getWalletHistory.mdandrules/getWalletTokenBalancesPrice.md. - Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore potentially malicious instructions embedded in transaction metadata or NFT names.
- Capability inventory: The skill uses
Bash(via curl) to fetch data andReadto access local rules. - Sanitization: Absent. The skill relies on the agent's internal logic to interpret the structured JSON responses.
- Context: This is a standard risk for any skill that reads public blockchain data. The skill's primary purpose is data retrieval, and it does not grant any dangerous execution capabilities based on the ingested data.
Audit Metadata