go-writing-code

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill mandates a five-step verification protocol in SKILL.md and references/post-change-protocol.md that requires the agent to execute shell commands including 'go build', 'go test', and 'golangci-lint' on the workspace code.
  • Ingestion points: The agent acts on Go source code files modified or created based on user-provided instructions in the conversation context.
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to disregard potential malicious instructions embedded in the code being processed.
  • Capability inventory: The agent is granted the capability to compile and execute code via the Go toolchain and run external linting utilities.
  • Sanitization: No sanitization, static analysis, or validation of the code is required before the build and test commands are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:50 AM