propensity-scoring-realtime
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill contains educational content and logic templates for propensity scoring.
- [PROMPT_INJECTION]: Analyzed for potential indirect prompt injection surface.
- Ingestion points: The
update_score_from_messagefunction inSKILL.mdprocesses untrusted conversation messages. - Boundary markers: Absent.
- Capability inventory: No dangerous operations are present; the skill only calculates scores and triggers internal notification placeholders.
- Sanitization: Employs regex signal extraction for passive analysis of input strings.
Audit Metadata