newsletter-voice
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate analysis of writing patterns and structural elements to create a markdown profile for the user. It functions by reading project files and processing chat inputs without executing code or accessing remote resources.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content in the form of user-provided newsletter samples for analysis, which serves as a potential surface for indirect prompt injection.
- Ingestion points: Step 1 processes user-pasted newsletter samples; Step 2 reads project files
voice.mdandabout-me.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the analysis logic.
- Capability inventory: The skill is limited to writing a text file (
newsletter-voice.md) to the local project directory. - Sanitization: No explicit sanitization or validation of the input content is performed before the agent analyzes the text.
Audit Metadata