featured-snippet-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential indirect prompt injection surface through its external data ingestion points. Ingestion points: In SKILL.md, the agent is instructed to perform Google searches to extract featured snippet text (Step 1) and retrieve content from an untrusted web page URL (Step 3). Boundary markers: The instructions lack explicit boundary markers or directives telling the agent to ignore embedded instructions within the fetched data. Capability inventory: The agent uses web browsing and search tools to read external content and generate content rewrites. Sanitization: No input filtering or content sanitization is performed on the ingested webpage or snippet content prior to processing.
Audit Metadata