research-word-etymology
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites, which constitutes an indirect prompt injection surface (Category 8).
- Ingestion points: Steps 1 and 5 utilize WebSearch and WebFetch to gather data from etymological resources (e.g., etymonline.com) and to investigate folk etymologies from general web results.
- Boundary markers: The skill does not define explicit delimiters or boundary markers to isolate external search results from the agent's core instructions.
- Capability inventory: The agent's tools are limited to reading and searching (Read, Grep, Glob, WebFetch, WebSearch). It lacks the capability to execute system commands, write to the filesystem, or access sensitive credentials.
- Sanitization: No explicit sanitization or instructions to disregard embedded commands in the fetched content are present, though the specific focus on linguistic data extraction limits the likelihood of a high-impact exploit.
Audit Metadata