ai-tech-rss-fetch

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'feedparser' Python package via pip to handle RSS and Atom feed parsing.
  • [PROMPT_INJECTION]: The skill processes untrusted metadata from external RSS feeds, creating an indirect prompt injection surface.
  • Ingestion points: Content is ingested from remote URLs by 'scripts/rss_subscribe.py' using the 'feedparser' library.
  • Boundary markers: No explicit delimiters or boundary markers are used to separate the external feed content from system instructions.
  • Capability inventory: The skill can perform network requests to arbitrary feed URLs and has write access to a local SQLite database.
  • Sanitization: The script performs basic string and URL normalization but does not implement content filtering or sanitization to detect or prevent malicious instructions embedded in the feed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 02:09 PM