stophy-web
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@stophy/cliNode.js package vianpxto perform search operations. This is a vendor-provided tool designed for the skill's primary research and scraping functionality. - [COMMAND_EXECUTION]: The skill uses the
Bashtool to executestophyCLI commands, allowing the agent to retrieve research data and trends from the web. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources, specifically Google search results, which could theoretically contain malicious instructions designed to influence the agent.
- Ingestion points: External research data enters the agent's context through the output of the
stophy scrapecommand as described inSKILL.md. - Boundary markers: There are no explicit markers or instructions provided to distinguish the scraped content from the agent's internal instructions.
- Capability inventory: The skill has access to the
Bashtool, providing a command execution surface for potential follow-on actions. - Sanitization: No specific validation or sanitization of the scraped data is mentioned before the agent processes it.
Audit Metadata