onboard-site

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted external data.\n
  • Ingestion points: The skill uses list_sitemaps_enhanced to read XML data from remote servers and references an seo-audit skill that parses live website content.\n
  • Boundary markers: No explicit boundaries, delimiters, or instructions are provided to the agent to treat external content as data only or to ignore embedded instructions within that content.\n
  • Capability inventory: The agent has the ability to perform network submissions via submit_sitemap and other onboarding tools, which could be abused if an injection is successful.\n
  • Sanitization: The instructions do not define any sanitization, validation, or filtering of the content ingested from the target website or sitemap.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 04:56 AM
Security Audit — agent-trust-hub — onboard-site