x-analytics-import

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external CSV files, creating an indirect prompt injection surface where malicious data could influence agent behavior.
  • Ingestion points: scripts/x_analytics_import.py parses user-supplied CSV files for account, content, and video analytics.
  • Boundary markers: Instructions in SKILL.md define strict boundaries between raw data and public-safe reports, though data-level delimiters are not programmatic.
  • Capability inventory: The skill is limited to local file system writes for artifacts and reports; it lacks network access or arbitrary shell execution capabilities.
  • Sanitization: The parser enforces strict schema validation, type checking for dates and numbers, and header normalization to prevent malformed data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 07:07 PM
Security Audit — agent-trust-hub — x-analytics-import