soul-audit
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by gathering untrusted user input via an interview and writing it to local configuration files that define the agent's identity and access policies.
- Ingestion points: User responses during the six interview phases described in SKILL.md.
- Boundary markers: None; user input is directly interpolated into the configuration file templates.
- Capability inventory: The skill utilizes the put_page tool to create and modify local configuration files.
- Sanitization: No input validation or sanitization is specified for the user-provided strings.
Audit Metadata