stophy-search
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external search results and web pages, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: External web content is retrieved via the
stophy searchcommand as described inSKILL.md. - Capability inventory: The agent utilizes the
Bashtool to execute shell commands, providing a significant capability surface if influenced by malicious input. - Boundary markers: The instructions do not define delimiters or specific markers to help the agent distinguish between its instructions and the retrieved data.
- Sanitization: No sanitization or validation of the external content is mentioned before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill relies on the execution of the
stophyCLI andnpx @stophy/cli, which involves running external code. These tools are provided by the vendor for the skill's primary purpose.
Audit Metadata