erc8004-on-abstract
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a reference and implementation guide for the ERC-8004 protocol. All code snippets and contract addresses are consistent with the stated purpose of enabling onchain agent identity and reputation.
- [SAFE]: Secret management follows industry standards by using environment variables (e.g.,
process.env.PRIVATE_KEY) to handle sensitive wallet information. - [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting external agent metadata and onchain feedback data.
- Ingestion points: External agent metadata JSON files (referenced in
SKILL.mdandreferences/agent-uri-schema.md) and reputation feedback entries read from theReputationRegistrycontract. - Boundary markers: None explicitly defined in the provided implementation examples, though the protocol enforces a JSON schema for agent URIs.
- Capability inventory: Writing to and reading from smart contracts on the Abstract mainnet using the
viemlibrary. - Sanitization: The documentation provides explicit guidance on mitigating malicious data (Sybil attacks) by filtering reputation queries through trusted
clientAddresses.
Audit Metadata