skills/lgtm-hq/ai-skills/test/Gen Agent Trust Hub

test

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of various test runners and framework-specific commands (e.g., uv run lintro, bun test, cargo test, go test). It specifically instructs the agent to run project-defined scripts found within package.json.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon configuration files and metadata from the project environment, which presents a surface for indirect instructions.
  • Ingestion points: Project configuration files (e.g., jest.config.js, pyproject.toml, package.json) and directory structures.
  • Boundary markers: None identified.
  • Capability inventory: File system read access and command execution (shell).
  • Sanitization: None identified; the skill assumes project files are valid and non-malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:26 AM
Security Audit — agent-trust-hub — test