sitemap-manager

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill fetches and parses external XML sitemaps and robots.txt files from user-provided URLs (SKILL.md, Mode 1).
  • Boundary markers: Absent; the instructions do not provide delimiters or specific guidance for the agent to ignore malicious instructions that might be embedded within XML tags or comments in the fetched files.
  • Capability inventory: The skill has the capability to perform network requests (sampling 20-50 URLs for health checks) and executes a script for auditing.
  • Sanitization: Absent; there is no mention of XML schema validation or filtering of content ingested from the sitemaps.
  • [EXTERNAL_DOWNLOADS]: The skill downloads content from arbitrary URLs provided at runtime. It is instructed to sample and visit 20-50 URLs discovered within those sitemaps to check HTTP status codes. This behavior could be exploited to perform Server-Side Request Forgery (SSRF) if the sitemap contains internal network addresses (e.g., localhost or cloud metadata services).
  • [REMOTE_CODE_EXECUTION]: The skill identifies 'tech-seo-auditor.py' as a script used for URL health checking. However, the source code for this script is not provided in the skill package, making its logic and security unverifiable.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — sitemap-manager