seo-sitemap

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted data from external sources.
  • Ingestion points: The skill utilizes the 'WebFetch' tool to retrieve XML sitemap content from user-provided URLs in 'Mode 1: Analyze Existing Sitemap'.
  • Boundary markers: The instructions do not define clear boundary markers or provide explicit instructions to the agent to disregard natural language commands that might be embedded within the fetched XML data.
  • Capability inventory: The skill's environment includes 'Bash', 'Write', 'Read', 'Grep', and 'Glob' tools as defined in the frontmatter, which represent a significant set of capabilities if the agent's logic is subverted.
  • Sanitization: There is no requirement or instruction for sanitizing, escaping, or validating the content retrieved from external URLs before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:00 AM
Security Audit — agent-trust-hub — seo-sitemap