skills/peachest/skills/gopls-refactor/Gen Agent Trust Hub

gopls-refactor

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to perform refactoring tasks. It uses sed -i for text replacement, gopls for semantic renaming, and the Go toolchain (go build, go test, go install) for verification and dependency management. While these are standard developer tools, their use on local files constitutes a powerful capability set.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes user-controlled Go source code.
  • Ingestion points: The skill reads Go source files to identify symbols and executes go generate on the package directory (found in REGENERATE.md and SKILL.md).
  • Boundary markers: There are no explicit boundary markers or safety instructions to ignore potentially malicious directives inside comments or source code.
  • Capability inventory: The skill has the capability to execute arbitrary commands via go generate, modify files via sed, and compile/run code via go build and go test.
  • Sanitization: There is no sanitization of the commands found within //go:generate directives before they are executed by the go generate command.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the gopls tool from golang.org/x/tools/gopls@latest. This is a download from a well-known and official repository for Go development tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 10:42 AM