soul-create
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external content (e.g., writing samples, blog posts, essays) to generate a persona profile.
- Ingestion points: The skill reads from user-provided source material and file paths like
./samples/*.md. - Capability inventory: The skill performs filesystem writes to create or update
SOUL.mdfiles. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the processed source material.
- Sanitization: There is no evidence of input sanitization or filtering to prevent malicious instructions hidden within source text from being incorporated into the generated persona definition.
Audit Metadata