daily-briefing
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for the agent to aggregate and prioritize sales-related information. No evidence of malicious intent, obfuscation, or unauthorized access was found.
- [PROMPT_INJECTION]: The skill processes data from external sources (Email, CRM, Calendar), which is a common surface for indirect prompt injection. In this context, the risk is minimal as the skill's capabilities are limited to text summarization and do not include high-risk operations like code execution or data exfiltration.
- Ingestion points: Calendar events, CRM records, Email messages (referenced in SKILL.md).
- Boundary markers: None.
- Capability inventory: None (summarization only).
- Sanitization: None.
Audit Metadata