skills/biomejs/biome/testing-codegen/Gen Agent Trust Hub

testing-codegen

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for testing and project maintenance, such as cargo test, just gen-rules, and cargo insta review. These are legitimate development tasks within the Biome project's infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project files, test fixtures, and snapshots, which are external data sources. The skill includes instructions for human review and validation (e.g., inspecting snapshot changes) to mitigate risks associated with processing these files. 1. Ingestion points: Test fixtures (.snap, .json, .jsonc, .md) and source code comments. 2. Boundary markers: Uses explicit diagnostic expectation comments like should generate diagnostics to delimit test intent. 3. Capability inventory: Filesystem modification and execution of build/test tools via cargo and just. 4. Sanitization: Employs manual review checkpoints for snapshots and generated artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:47 PM