codeguard-solidity

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes solhint and prettier shell commands to perform static analysis and code formatting on Solidity projects. These actions are transparently documented and aligned with the tool's core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external .sol files, creating a potential surface for indirect prompt injection. Ingestion points: Reading Solidity source code and project configuration files. Boundary markers: Missing explicit delimiters for file content interpolation in prompts. Capability inventory: Local file reading/writing and shell command execution. Sanitization: Includes instructions for path validation and requires user confirmation for all modifications after reviewing a file diff.
  • [DYNAMIC_EXECUTION]: The skill performs runtime construction of shell commands by interpolating project-specific file paths into command templates, such as replacing {file} placeholders with authorized local paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 04:47 AM