blog-feed-monitor
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content from arbitrary external URLs provided by the user to discover and parse RSS/Atom feeds in
scripts/scrape_blogs.py.\n- [EXTERNAL_DOWNLOADS]: It communicates with external APIs includingapi.apify.comand the vendor-specific proxy atapi.gooseworks.aito perform scraping tasks.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from external websites, creating a surface for indirect prompt injection.\n - Ingestion points: Raw HTML and XML content is fetched from external blog URLs in
scripts/scrape_blogs.py.\n - Boundary markers: The script does not wrap the scraped text in delimiters or provide specific instructions for the agent to treat the data as untrusted.\n
- Capability inventory: The script uses the
requestslibrary for network access and writes the scraped content to stdout for processing by the agent.\n - Sanitization: No filtering or sanitization is performed on the scraped titles, descriptions, or content before it is passed to the agent.
Audit Metadata