hypothesis-builder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for a marketing workflow (mapping personas, signals, and angles into a testing matrix).
- [NO_CODE]: No scripts, external dependencies, or command executions are present in the skill definition.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied data such as Ideal Customer Profile (ICP) definitions, buyer personas, and market signals. While the instructions do not include specific delimiters or boundary markers for this external data, the skill does not utilize any tools or have capabilities (such as network access or file system modification) that could be misused if malicious instructions were present in the input data. The attack surface is limited to the text output itself.
Audit Metadata