content-research-writer
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (MEDIUM): The skill uses untrusted web content to generate external-facing communications such as newsletters and social media posts. | Ingestion points: Web search results and user-provided writing samples in SKILL.md Steps 2 and 3. | Boundary markers: Absent; there are no instructions to the agent to disregard commands found within the research material. | Capability inventory: Generation of text for newsletters, tweets, and blog posts (external outputs); no shell execution or file-system modification capabilities. | Sanitization: Absent; external data is integrated into the output flow without validation or filtering.
- NO_CODE (SAFE): This skill contains no executable scripts, binaries, or external code dependencies.
Audit Metadata