review-go

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes standard version control and Go toolchain commands (git, grep, go build, go vet) to perform static analysis and identification of project technologies.\n- [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill ingests untrusted code from git diffs and source files, which could contain malicious instructions designed to subvert the agent's logic or exploit its capabilities.\n
  • Ingestion points: Git diff outputs and Go source files within the repository being reviewed (SKILL.md)\n
  • Boundary markers: None identified in the provided instructions\n
  • Capability inventory: git, grep, go build, go test, golangci-lint (SKILL.md)\n
  • Sanitization: None identified; the agent is instructed to read and process raw code content.\n- [SAFE]: The skill uses a verification step involving 'go test -v -race', which is a standard development practice but should be used with caution on untrusted codebases.\n- [SAFE]: External skill dependencies (beagle-go:*) are used to extend functionality for specific technology stacks like BubbleTea and Prometheus.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 05:53 AM
Security Audit — agent-trust-hub — review-go