stophy-build-search

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external web pages, news articles, and image metadata which is then processed by the AI agent. This creates an attack surface where malicious instructions embedded in third-party websites could influence the agent's behavior.
  • Ingestion points: Data enters the agent's context through search results returned by stophy.search() (web, news, and images) and scraped page text (markdown) retrieved via scrapeOptions in SKILL.md.
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or specific instructions to the agent to disregard instructions potentially contained within the fetched search data.
  • Capability inventory: The skill demonstrates network capabilities to interact with the Stophy search API and can be used to ground agent responses in external data.
  • Sanitization: No sanitization, filtering, or validation of the retrieved web content is shown in the integration examples, allowing raw third-party data to be passed directly to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:19 PM