alterlab-pra-consumer-insight
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to autonomously create and write multiple markdown files to the local project directory, such as personas (
{project}-persona-cards.md) and journey maps ({project}-journey-map.md). This is a core functionality for generating its research deliverables. - [PROMPT_INJECTION]: The skill utilizes external data sources by searching the web and reading existing project files. This functionality represents an indirect prompt injection surface where malicious instructions embedded in external content could potentially influence the agent, although this is a standard risk for research-oriented agents.
- [DATA_EXPOSURE]: The skill instructions direct the agent to read existing project files, including campaign data and audience profiles, to provide context for its research. This is necessary for its primary purpose, and the agent is instructed to store results locally.
Audit Metadata