skill-10-identity-did
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational and provides architectural guidance for identity management without including executable scripts or commands.
- [DATA_EXPOSURE]: The instructions explicitly mandate privacy best practices, such as never storing PII on-chain, honoring GDPR right-to-erasure, and using selective disclosure proofs.
- [PROMPT_INJECTION]: No evidence of instructions designed to bypass agent safety filters or override system prompts was found.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execution. It references MCP tools and local documentation for project-specific logic.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external data such as DID documents, ENS text records, and Verifiable Credentials. However, it recommends standard verification practices (signature checking and schema compliance) to mitigate risks associated with untrusted data.
Audit Metadata