Skills
skills/sisodiabhumca/agent-skills/product-analytics-investigator/Gen Agent Trust Hub

product-analytics-investigator

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches product event data from official Amplitude (amplitude.com) and Mixpanel (mixpanel.com) API endpoints. These interactions are limited to data retrieval from well-known services.\n- [COMMAND_EXECUTION]: Executes the Python script investigate.py to process analytical data, calculate conversion funnels, and generate a summary report.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) by ingesting data from external APIs and files and interpolating it into markdown reports.\n
  • Ingestion points: investigate.py (via load_csv, fetch_amplitude, and fetch_mixpanel functions).\n
  • Boundary markers: Absent; event names and property values are placed directly into markdown tables without delimiters or warnings.\n
  • Capability inventory: investigate.py utilizes network access for data retrieval and file system access for reading source data and writing outputs.\n
  • Sanitization: Absent; the script does not validate or escape event-level data before including it in the final markdown memo.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 04:12 PM
Security Audit — agent-trust-hub — product-analytics-investigator