serpapi

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires passing an api_key as a query parameter on every request, which would force the agent to include a secret API key verbatim in generated requests/outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.95). At runtime the skill calls SerpApi via WebFetch and ingests the returned JSON fields (e.g., jobs_results[].description and google_shopping/amazon/ebay result text like titles/snippets/prices) into the agent’s LLM context; these are outsider-authored web/search content from third-party sources.