daily-briefing
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process data from external, untrusted sources such as calendar event descriptions, CRM notes, and email content.
- Ingestion points: Processes external data from Calendar (titles, descriptions), CRM (deal notes), and Email (subject lines/content) through specified connectors.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the prompt templates or execution flow.
- Capability inventory: The skill uses basic file tools (
Read,Glob,Grep) to interact with data. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the ingested external content before it is summarized for the user.
Audit Metadata