go-test-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill provides a surface for indirect prompt injection as it is designed to ingest and process untrusted code (Go files/test requests) while having access to sensitive tools.
  • Ingestion points: User requests and code provided for test generation.
  • Boundary markers: Absent; no instructions provided to the agent to ignore instructions embedded within the data it processes.
  • Capability inventory: Includes Bash, Write, Edit, Read, and Grep, which allow for significant system interaction if an injection is successful.
  • Sanitization: No sanitization or validation logic is defined in the instruction set.
  • [No Executable Code] (SAFE): The provided skill consists only of a markdown file (SKILL.md) with metadata and documentation. No companion scripts (.py, .js, .sh) or binaries were included in the package.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM