solana-dev@r4
VERIFIED· install onlyPublisher claims: "Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my Solana program", "deploy to devnet", "send a v1 transaction", "support larger transactions", "fix maxSupportedTransactionVersion", or "explain Solana concepts" (rent, accounts, PDAs, CPIs). Also for program architecture (state layout, compute units, throughput, naming), quick on-chain lookups via public RPC + curl, gasless or sponsored-fee transactions (Kora), server-side signing with KMS/Turnkey/Privy/Fireblocks (Solana Keychain), and issuing stablecoins or allowlisted tokens (Mosaic). Covers wallets, Anchor/Pinocchio, Codama clients, Surfpool/LiteSVM/Mollusk testing, security review, and v1 transactions (SIMD-0385). Prefers @solana/kit 8 plugin clients building transaction v1 by default, @solana/kit-plugin-wallet + @solana/react for wallets, web3.js v3 as the legacy migration target, and Surfpool for local networks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since r3
vet-skills diff solana-dev r3 r4In the sandbox, this version reached for nothing r3 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is solana-dev@r4 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-22 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
codex mcp add solana-mcp-server -- npx -y mcp-remote https://mcp.solana.com/mcpFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.codex mcp add solana-mcp-server -- npx -y mcp-remote https://mcp.solana.com/mcpFix: Pin versions and sources; vendor anything fetched at install time.gemini mcp add --transport http solana-mcp-server https://mcp.solana.com/mcpFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.claude mcp add --transport http solana-mcp-server https://mcp.solana.com/mcpFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.