daily-briefing
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, which could contain adversarial instructions.
- Ingestion points: SKILL.md (Step 1: Gather Context) lists Calendar events, CRM pipeline data, Email messages, and Enrichment signals as data sources.
- Boundary markers: The instructions do not specify any delimiters or negative constraints to prevent the agent from following instructions embedded in the external data.
- Capability inventory: Based on SKILL.md, the agent's capabilities include reading data and generating reports/briefings; it does not appear to have direct file-write or shell execution capabilities in this specific context.
- Sanitization: There is no evidence of data sanitization or filtering logic to remove potentially malicious prompts from the retrieved external content.
Audit Metadata