NYC

readme-updater

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect prompt injection risk via data ingestion.
  • Ingestion points: Reads package.json, .env.example, docker-compose.yml, and git diffs (e.g., auth.service.ts).
  • Boundary markers: None explicitly defined in the prompt logic to differentiate between code structure and embedded malicious instructions.
  • Capability inventory: The skill uses Read, Write, Edit, and Grep tools to modify project files.
  • Sanitization: No evidence of sanitization or escaping of external content before it is processed by the LLM to suggest README updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:25 PM