niche-researcher
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely through structured instructions and templates. No executable scripts (.py, .js, .sh) are included or referenced for execution.
- [DATA_EXPOSURE]: The skill is designed to write research dossiers to a local directory (
memory/influencer/niche-researcher/) and promote key facts to a shared cache (memory/hot-cache.md). These are standard persistence mechanisms for the agent's internal memory and do not involve unauthorized exfiltration to external domains. - [PROMPT_INJECTION]: The skill ingests data about communities, including 'Insider Language' and 'Community Norms'. While this represents an indirect prompt injection surface (Category 8) where malicious content could be embedded in the data processed, the skill's primary function is research and documentation, and it lacks the high-privilege capabilities (like network access or arbitrary command execution) that would make such an injection critical. The risk is considered low and inherent to the skill's purpose.
Audit Metadata