serper-search

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external web content, creating a surface for potential injection attacks. Ingestion points: Organic search results retrieved via the Serper API (SKILL.md). Boundary markers: The skill advises summarizing and linking to results but does not define strict data delimiters or boundary markers for the search snippets. Capability inventory: The agent performs network requests to fetch search data. Sanitization: No specific sanitization or filtering logic is described for the retrieved search content.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to google.serper.dev to fetch search data. Serper is a well-known service for providing Google Search results to AI applications.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 04:45 AM