soultrace
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: Performs network requests to
https://soultrace.app/api/agentto transmit user answers and receive assessment questions. This communication targets the vendor's official domain and is the primary intended function of the skill. - [PROMPT_INJECTION]: Analyzed for indirect prompt injection surface as the skill processes user answers.
- Ingestion points: User-provided responses to personality questions (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Outbound network requests to
soultrace.app. - Sanitization: Present. The skill instructs the agent to map all user input to a strict 1-7 numeric Likert scale before transmission, which mitigates the risk of instructions embedded in user answers influencing the API or the agent's behavior.
Audit Metadata