Slv Grpc Geyser
WarnAudited by ClawScan on May 10, 2026.
Overview
The skill is mostly aligned with deploying Solana Geyser nodes, but it directs the agent to run high-impact Ansible playbooks from an unreviewed local template directory.
Install only if you trust and have reviewed the SLV template playbooks under ~/.slv/template that the agent will execute. Confirm the exact playbook path and variables, use --check first, use a dedicated SSH key for the target server, and review the setup script before running it.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If the local template directory is stale, tampered with, or not the one the user expects, the agent could run unreviewed infrastructure automation against a server.
The agent is told to execute the latest local template playbooks outside the reviewed skill package. Those playbooks are not included in the supplied manifest and no pinning, checksum, or provenance check is shown, while Ansible playbooks can make broad changes to remote servers.
All playbooks are stored in `~/.slv/template/{version}/ansible/`... `TEMPLATE_DIR=$(ls -d ~/.slv/template/*/ | sort -V | tail -1)` ... Do NOT use the skill's own `ansible/` directory for execution.Before allowing execution, verify the exact ~/.slv/template version, source, and playbook contents; pin a known-good version and run Ansible with --check first.
Approved commands can affect node availability or configuration.
The skill gives the agent authority to run Ansible playbooks that can deploy, stop, restart, or rebuild a node, but it also instructs the agent to ask for confirmation and offer a dry-run.
Confirm before destructive actions: Always confirm before stop, restart, or plugin rebuild ... Offer `--check` (dry-run) first ... On confirmation, run ... `ansible-playbook`
Review the generated inventory, variables, and exact playbook command before approving; prefer a dry-run first.
A mistaken or overbroad SSH key could give the agent access to more infrastructure than intended.
The skill uses SSH credentials and may use elevated privileges on a fresh server. This is expected for server deployment, but it is sensitive authority.
`ssh_key_path` — Path to SSH private key (default: `~/.ssh/id_rsa`) ... `ansible-playbook -i inventory.yml cmn/add_solv.yml ... --become`
Use a dedicated SSH key limited to the target server, avoid sharing private key contents, and confirm any --become operation.
Running the setup script may install packages through pip, Homebrew, apt, or dnf.
The setup script can install local prerequisites if the user runs it. This is purpose-aligned and disclosed, but it changes the local environment.
`pip3 install --user ansible-core` ... `sudo apt-get update && sudo apt-get install -y ansible-core`
Inspect the setup script and run it manually only if you are comfortable with the package manager actions.