urgency-creation
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection through its processing of untrusted user data. * Ingestion points: Processes user-provided context such as prospect_deadline, sentiment, and intent in the implementation logic. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the messaging templates. * Capability inventory: The skill is limited to text generation; no command execution, network requests, or file system operations are present. * Sanitization: No input validation or escaping logic is implemented in the provided pseudo-code.
Audit Metadata