seo-aeo-diagnostics

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) because its core functionality involves fetching and analyzing content from external, untrusted websites.
  • Ingestion points: Data is ingested from external URLs via the web_fetch and browser tools across all diagnostic sub-modules, such as technical-foundation/SKILL.md and search-accessibility/SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or "ignore embedded instructions" warnings when processing the retrieved HTML or metadata, which could allow instructions hidden in a website's source code to influence the agent's behavior.
  • Capability inventory: The skill uses network retrieval tools to perform its audits. It does not have access to sensitive local files, the ability to write to the file system, or arbitrary command execution capabilities.
  • Sanitization: There is no evidence of sanitization, filtering, or escaping of the fetched content before it is processed by the LLM for diagnosis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:51 AM