svm
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to act as a protocol expert by routing information requests through a specific set of tools (
heliusKnowledge,fetchHeliusBlog,searchSolanaDocs,getSIMD,readSolanaSourceFile). These tools are documented to fetch content from public, well-known repositories (e.g.,anza-xyz/agave,solana-foundation/simds) and Helius Labs' official blog. - [SAFE]: The skill explicitly prohibits file writing operations ('Never write files') and focuses on synthesized conversational responses, reducing the risk of local file system manipulation.
- [SAFE]: All referenced external sources are well-known technology entities (Helius Labs, Solana Foundation, Anza, Jump Crypto). No unverifiable third-party dependencies or remote code execution patterns were detected.
- [SAFE]: The instructions contain clear boundaries and redirects for implementation-specific questions, ensuring the agent stays within its intended pedagogical scope.
- [SAFE]: Frontmatter configuration properly scopes the environment to use the
helius-mcpserver, and the provided remediation advice for users is standard setup guidance for the platform.
Audit Metadata