social
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided content such as bios, websites, and news stories to learn a writing voice and extract facts. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the source material. * Ingestion points: External websites, user bios, and news articles mentioned in the voice-learning and writing steps. * Boundary markers: The skill does not define specific boundaries or ignore-instructions for the external data. * Capability inventory: Analysis shows no usage of file system, network, or shell command tools. * Sanitization: There are no instructions to sanitize or filter the content of ingested external sources.
Audit Metadata