go-test-fixer

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Go and Python scripts (.claude/scripts/test-conversion/main.go and .claude/scripts/move_code_section.py) to perform table-test conversion and code section relocation.
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools including go fmt, go test, and golangci-lint to format code and verify the integrity of refactored tests.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8) due to its core function of processing external code files.
  • Ingestion points: Go source and test files (test_file.go) and project directories read by the agent and processing scripts.
  • Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to ignore instructions embedded in the code files being processed.
  • Capability inventory: The skill possesses file-writing capabilities through its scripts and arbitrary command execution via the go test and go run tools.
  • Sanitization: There is no evidence of sanitization or validation of the content within the Go files before they are processed or used in refactoring operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:41 AM
Security Audit — agent-trust-hub — go-test-fixer