academic-trend-research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external scholarly databases, news portals, and web search engines (Exa, Tavily, Google News), creating an attack surface where maliciously crafted external content could attempt to influence the agent's research output.
- Ingestion points: External data enters the agent's context through the outputs of scholarly and web search tools mentioned in the SKILL.md and API map.
- Boundary markers: The skill lacks explicit prompt delimiters or boundary markers for external data, although it provides guidelines to separate factual observations from analysis.
- Capability inventory: The skill's capabilities are limited to data retrieval and synthesis using the
sandbase_call_toolgateway. - Sanitization: There are no documented instructions for sanitizing or escaping ingested content before synthesis.
Audit Metadata