data-analyst

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data.
  • Ingestion points: The script scripts/analyze_missing_values.py reads user-provided CSV files using pd.read_csv(filepath).
  • Boundary markers: Absent. There are no delimiters or instructions to the agent to disregard embedded commands within the CSV data.
  • Capability inventory: The skill can read local files and write results to a JSON file via analyze_missing_values(filepath, output_json). It does not have network access or arbitrary command execution capabilities.
  • Sanitization: Absent. The script processes column names and values from the CSV without sanitization before returning the analysis results to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 12:23 PM