bigquery-table-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • No Code (SAFE): The skill consists solely of a markdown configuration file and does not ship with any executable scripts or binaries.
  • Indirect Prompt Injection (SAFE): While the skill defines a broad capability surface by allowing the use of gcloud bash commands, it does not contain instructions that bypass safety filters or exfiltrate data. 1. Ingestion points: User requests via LLM context. 2. Boundary markers: Absent. 3. Capability inventory: Read, Write, Edit, Bash(gcloud:*). 4. Sanitization: Handled by underlying agent safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM