review-go

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tools including git, grep, go build, go vet, and golangci-lint to analyze and verify the codebase.
  • [REMOTE_CODE_EXECUTION]: The skill runs go test -v -race in Step 7, which executes the project's own code to verify fixes. This is a standard and expected behavior for a code review tool.
  • [PROMPT_INJECTION]: The skill evaluates source code files and git diffs, creating an indirect prompt injection surface where instructions hidden in code could influence agent behavior.
  • Ingestion points: Processes output from git diff (Step 1) and reads project source files (Step 6).
  • Boundary markers: Absent. The skill does not define specific delimiters to separate untrusted code from its own instructions.
  • Capability inventory: Can execute shell commands via the Go toolchain and spawn sub-agents using the Task tool.
  • Sanitization: Absent. The skill does not mention sanitizing or escaping content from the codebase before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:16 AM