NYC

accelint-ts-testing

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill identifies a workflow for auditing user-provided test files, which represents a surface for indirect prompt injection.
  • Ingestion points: AGENTS.md specifies a workflow for reviewing existing test code provided by the user (file paths or direct code input).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in the user's test files are defined in the provided snippets.
  • Capability inventory: The agent generates reports and suggestions based on the analyzed code. No direct shell execution or network calls are triggered by the analysis itself.
  • Sanitization: No sanitization or escaping mechanisms for the user-provided code are mentioned before it is processed by the agent's LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 10:47 PM