dns-connector
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from an external website, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent's context from the dns-shop.ru website via the
dns_searchanddns_cardtools. - Boundary markers: The documentation does not specify the use of delimiters or instructions to the agent to ignore any commands that might be embedded within the scraped product data.
- Capability inventory: The skill is capable of rendering web pages and extracting data from the DOM using the Chrome DevTools Protocol (CDP).
- Sanitization: There is no evidence in the skill description of sanitization, filtering, or validation performed on the retrieved content before it is provided to the agent.
Audit Metadata