site-architecture

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external XML data from sitemaps, which represents a potential attack surface for indirect prompt injection if a malicious sitemap contains instructions targeting the agent.
  • Ingestion points: The scripts/sitemap_analyzer.py script fetches external URLs, and SKILL.md instructs the agent to read and analyze sitemap content.
  • Boundary markers: The instructions do not explicitly define boundaries or provide warnings for the ingested sitemap data.
  • Capability inventory: The skill possesses network fetching capabilities via urllib.request and XML parsing via xml.etree.ElementTree in scripts/sitemap_analyzer.py.
  • Sanitization: The analysis script implements XML parsing error handling and namespace stripping.
  • [EXTERNAL_DOWNLOADS]: The scripts/sitemap_analyzer.py utility fetches content from user-provided URLs to perform its analysis. This behavior is a core functional requirement of the skill's purpose and does not involve downloading executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — site-architecture