skills/ortus-boxlang/skills/bx-rss/Gen Agent Trust Hub

bx-rss

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection through the parsing of external, untrusted RSS/Atom feed data.
  • Ingestion points: Content is fetched from arbitrary external URLs using the rss() BIF or the bx:feed component with action="read" in SKILL.md.
  • Boundary markers: No boundary markers or special guardrails are implemented to isolate external content or instruct the model to ignore potential embedded instructions.
  • Capability inventory: The skill possesses capabilities to write data to local files (fileWrite) and render output via writeOutput or HTTP endpoints.
  • Sanitization: The raw text contents of the feed (such as titles, descriptions, and items) are handled and displayed directly without filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:02 AM
Security Audit — agent-trust-hub — bx-rss