gs-advanced-search
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted search results from Google Scholar, which represents an attack surface for indirect prompt injection.
- Ingestion points: Web content including titles, snippets, and metadata are extracted from the DOM of scholar.google.com in Step 3 (evaluate_script) of SKILL.md.
- Boundary markers: There are no explicit boundary markers or instructions to isolate the data retrieved from external search results from the agent's operational instructions.
- Capability inventory: The skill possesses browser navigation and JavaScript execution capabilities through the mcp__chrome-devtools__navigate_page and evaluate_script tools as documented in SKILL.md.
- Sanitization: The skill does not implement sanitization or filtering for the data extracted from the external search provider before it is returned to the agent context.
Audit Metadata