research-word-etymology
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from third-party websites using WebSearch and WebFetch tools. This creates an attack surface for indirect prompt injection if external resources contain malicious instructions. • Ingestion points: Web search results from linguistic databases and web sources mentioned in SKILL.md. • Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands in fetched data. • Capability inventory: Restricted to information retrieval and local reading; no file-write or shell execution tools are enabled. • Sanitization: No sanitization of retrieved web content is specified.
Audit Metadata