conference-speaker-scraper

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Includes a Python script (scripts/scrape_speakers.py) that performs scraping logic via command-line arguments.
  • [SAFE]: Utilizes environment variables for API tokens, following secure development practices for credential management.
  • [SAFE]: Communicates with the vendor's API and Apify (a well-known service), which is considered safe behavior for this skill's use case.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the script ingests and parses untrusted external web content.
  • Ingestion points: Conference URLs processed by requests.get in scripts/scrape_speakers.py.
  • Boundary markers: No specific delimiters used for the scraped text in output.
  • Capability inventory: Performs network requests and writes results to stdout/files.
  • Sanitization: Implements basic HTML tag removal and character limits on biography text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:48 AM