social-voice
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a utility for analyzing writing style and managing a local configuration file (social-context.md). It performs no network operations, accesses no sensitive system files, and includes no obfuscated or remote code.
- [PROMPT_INJECTION]: The skill processes untrusted user-provided writing samples (Workflow Step 1) and uses the results to modify a local file (Workflow Step 9). While this creates a surface for indirect prompt injection, the risk is assessed as safe given the analytical constraints of the instructions. 1. Ingestion points: User-provided writing samples gathered in Step 1 of the Workflow. 2. Boundary markers: None explicitly defined to separate input from agent instructions. 3. Capability inventory: File write access to social-context.md in Step 9. 4. Sanitization: No explicit validation or sanitization of input samples.
Audit Metadata