dineway-site-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites, creating a surface for indirect prompt injection attacks where malicious content on a crawled site could attempt to influence agent behavior.
  • Ingestion points: Untrusted content is gathered from public web pages, live Search Engine Results Pages (SERPs), and competitor websites.
  • Boundary markers: While the skill uses a "bounded same-origin scope" for crawling, it does not explicitly define delimiters to isolate external content from the agent's instructions.
  • Capability inventory: The skill possesses the ability to write to the local filesystem (under .dineway/content/) and invoke Content Pipeline MCP tools.
  • Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external sources before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The workflow involves fetching data from external SEO and crawling services.
  • Evidence: The instructions reference using well-known services such as Firecrawl and DataForSEO for large-scale data collection and SERP analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:29 AM
Security Audit — agent-trust-hub — dineway-site-analysis