voice-dna-creator
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's operations are consistent with its described functionality and stated purpose of analyzing writing style.
- [PROMPT_INJECTION]: The skill processes untrusted data in the form of user-provided writing samples, creating a theoretical surface for indirect prompt injection. However, given the skill's purpose and limited capabilities, this is considered a standard architectural characteristic rather than a vulnerability.
- Ingestion points: Writing samples are collected via text input or knowledge folder files as described in Step 1.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the analysis steps.
- Capability inventory: The skill is instructed to save the synthesized profile to a local JSON file (
/context/voice-dna.json). - Sanitization: No specific content filtering or sanitization of the input text is performed before analysis.
Audit Metadata