blockchain-data-indexing
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from blockchain RPC providers and event logs. It lacks explicit instructions to use boundary markers or delimiters when interpolating this external data into agent prompts, which creates a surface for indirect prompt injection.
- Ingestion points:
SKILL.md(RPC polling logic),custom_indexer.py(processes logs viaw3.eth.get_logs), andreferences/event-processing.md(event decoder logic). - Boundary markers: Absent in prompt instructions and architecture examples.
- Capability inventory: The skill handles database write operations (
asyncpgincustom_indexer.py) and arbitrary network/RPC requests through Web3 providers. - Sanitization: Although 'Input validation' is listed as a security consideration in
SKILL.md, specific sanitization logic for the agent to follow when processing on-chain strings is not provided.
Audit Metadata