blog-scraper
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to retrieve RSS feeds from user-specified URLs and communicates with Apify's API (api.apify.com) for scraping fallback.
- [PROMPT_INJECTION]: The skill ingests untrusted data from external sources which could be used to deliver malicious instructions to the agent (Indirect Prompt Injection).
- Ingestion points: Untrusted data enters the script in
scripts/scrape_blogs.pythroughrequests.get()calls to user-provided URLs. - Boundary markers: The scraped content is not wrapped in delimiters or safety instructions before being presented to the agent.
- Capability inventory: The script uses the
requestslibrary for network operations but lacks more dangerous capabilities like file writing or command execution. - Sanitization: There is no sanitization of the content fetched from external feeds.
Audit Metadata