sm-bigquery-analyst

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill is susceptible to indirect prompt injection through its data ingestion and processing workflow. 1. Ingestion points: The agent ingests external data returned from bq query executions and natural language user questions as described in SKILL.md. 2. Boundary markers: Absent; there are no specified delimiters to separate instructions from untrusted table data during processing. 3. Capability inventory: The skill has the capability to execute system commands via the gcloud and bq CLI tools. 4. Sanitization: While SQL-level safety rules like 'SELECT-only' and dry-runs are mandated, there is no mechanism to sanitize the textual content of retrieved data for embedded instructions.
  • [COMMAND_EXECUTION] (MEDIUM): The skill relies on executing shell commands to interact with the host environment and BigQuery. Evidence: Multiple bash code blocks in SKILL.md demonstrate the use of gcloud and bq for environment verification and query execution.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 11:30 AM