Skills
skills/athina-ai/goose-skills/conference-speaker-scraper/Gen Agent Trust Hub

conference-speaker-scraper

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted text from external websites, which could contain malicious instructions aimed at influencing the agent's subsequent actions via indirect prompt injection.\n
  • Ingestion points: scripts/scrape_speakers.py (fetching HTML from user-supplied URLs via requests.get).\n
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to isolate untrusted data from the agent's logic.\n
  • Capability inventory: scripts/scrape_speakers.py has network access capabilities.\n
  • Sanitization: Basic HTML tag stripping is performed in the extract_text function, but it does not filter for prompt injection patterns.\n- [EXTERNAL_DOWNLOADS]: The skill fetches data from remote sources and relies on external dependencies.\n
  • It utilizes the requests library to fetch content from conference sites and interact with the Apify API.\n
  • It performs a POST request to api.apify.com to execute scraping tasks using the apify/cheerio-scraper actor.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:02 PM