daily-briefing
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from various external connectors, which can be used as a vector for indirect prompt injection attacks.
- Ingestion points: Calendars, tasks, tickets, pull requests, messages, and documents.
- Boundary markers: None found in the instructions to separate external data from system prompts.
- Capability inventory: The skill is limited to information gathering and summarization; it does not define script execution, file system writes, or network operations.
- Sanitization: No sanitization or filtering of external content is specified.
Audit Metadata