learn
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes curl as a fallback mechanism for data collection. This is a legitimate operation within the scope of a research skill and does not involve piping output to a shell.
- [EXTERNAL_DOWNLOADS]: The skill downloads content from web sources to the local file system (~/Downloads/) for the purpose of archiving and analyzing research materials.
- [PROMPT_INJECTION]: The skill ingests untrusted content from the web, which is an inherent surface for indirect prompt injection. The workflow mitigates this by instructing the agent to cross-verify claims across multiple sources and contexts.
Audit Metadata