research
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions define a process that involves ingesting untrusted data from external websites via the web_search tool.
- Ingestion points: Data enters the agent's context through the output of the web_search tool as described in the research process.
- Boundary markers: The instructions lack specific delimiters or instructions to treat search results as untrusted content.
- Capability inventory: The skill has the capability to perform iterative searches and synthesize answers based on external findings.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from the web before processing.
- [NO_CODE]: The skill contains only natural language instructions in markdown and does not ship with any executable scripts, binaries, or configuration files.
Audit Metadata