protobuf

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the buf CLI tool for common development tasks such as linting (buf lint), code formatting (buf format), dependency management (buf dep update), and schema generation (buf generate). These are standard operations for managing Protocol Buffer projects.
  • [EXTERNAL_DOWNLOADS]: The skill makes extensive use of the Buf Schema Registry (BSR) and remote generation plugins hosted on buf.build. It also provides standard installation instructions for the protoc compiler from official GitHub releases and language-specific plugins via established package managers (NPM, PyPI, Go). All external references target reputable and well-known domains associated with the Protocol Buffer ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided .proto files and project configuration files (buf.yaml, buf.gen.yaml).
  • Ingestion points: Reads project-specific .proto files, Buf configuration, and lock files.
  • Boundary markers: The skill does not explicitly define boundary markers for these files, relying on the structured nature of the files and the parsing capabilities of the buf CLI.
  • Capability inventory: Uses the buf CLI for linting, formatting, and code generation.
  • Sanitization: Standard toolchain parsing and linting are used to validate the files before processing.
  • Since this is the primary purpose of the skill and no malicious patterns were identified in the templates or instructions, this is considered a standard operational risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:28 AM