serp-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external search engine results (Google SERPs) via the DataForSEO API, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent receives external content such as page titles, snippets, and related searches from the
dataforseo_v3_serp_google_organic_live_advancedtool and its variants (SKILL.md). - Boundary markers: There are no explicit instructions provided to the agent to treat search results as untrusted or to use specific delimiters when processing this data.
- Capability inventory: The skill interacts with the SandBase gateway via
sandbase_call_tool(SKILL.md). - Sanitization: The instructions do not define any sanitization or validation steps for the content retrieved from external search results.
Audit Metadata