academic-scientific-research
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external scientific sources and web pages through search and extraction tools. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the retrieved content.
- Ingestion points: External data enters the agent context via the Tavily
search,extract,crawl, andresearchtools as described in the 'Capability Guidance' section of SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to treat retrieved tool output as untrusted data.
- Capability inventory: The skill uses network-read capabilities (
search,extract,map,crawl,research). It does not utilize file-write, code execution, or privilege escalation capabilities. - Sanitization: There are no explicit instructions to sanitize, escape, or filter retrieved content before it is processed by the agent.
Audit Metadata