content-research-writer
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, remote script downloads, or requests for sensitive information. The shell commands provided in the documentation (
mkdir,cd,touch) are standard setup steps for local file management and pose no security risk. - [PROMPT_INJECTION]: The skill involves a research component that ingests external data from the web to extract facts and citations. This establishes an indirect prompt injection surface (Category 8). However, as this is a core function of a research tool and no specific malicious triggers are present, the risk is handled within the AI's standard safety boundaries. No specific boundary markers are defined in the instructions for this external content, but the impact is minimal in the context of writing assistance.
Audit Metadata