go-performance-testing
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, workflows, and guidelines. It does not contain any executable scripts, automated tasks, or external code dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted performance data.
- Ingestion points: Benchmark raw output, profiles, and execution traces mentioned in SKILL.md and workflows/investigate-performance.md.
- Boundary markers: The skill does not define specific prompt delimiters for external performance data.
- Capability inventory: The instructions guide the agent to use shell tools including go test, go tool pprof, and go build as seen in references/performance-testing/examples.md.
- Sanitization: No specific sanitization or filtering logic is provided for the performance artifacts being analyzed.
- [NO_CODE]: The skill is composed of markdown files and YAML configuration only. No executable source code (e.g., Python, JavaScript) is distributed within the skill package.
Audit Metadata