fact-check
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
uvxto install and run theweb-foragerpackage anduv runto install theddgs(DuckDuckGo Search) library for search operations. These dependencies are directly related to the skill's primary function of evidence gathering. - [COMMAND_EXECUTION]: The skill executes shell commands to perform web searches and fetch page content using
curl. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from the open web, creating a surface for indirect prompt injection. Ingestion points: Article content fetched through
r.jina.aiand search snippets fromddgs. Boundary markers: Not specified in the instructions. Capability inventory: The skill has network access and the ability to execute shell commands viauv. Sanitization: No specific sanitization or filtering is defined for the external web content before it is analyzed by the agent.
Audit Metadata