NYC

tanstack-integration

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill involves analyzing the entire project codebase, which represents an untrusted data ingestion surface. 1. Ingestion points: 'look through the ENTIRE project' prompt in SKILL.md. 2. Boundary markers: Absent; no delimiters are used for the ingested code content. 3. Capability inventory: File reading and task creation via the 'bd' command. 4. Sanitization: Absent; no content escaping or validation is performed on analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:36 PM