meeting-briefing-anthropic

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest data from external sources like email, chat messages, and shared documents. This creates a potential surface for indirect prompt injection where malicious instructions could be embedded in those sources. 1. Ingestion points: SKILL.md Step 3 (Email, Chat, Documents, CLM, CRM). 2. Boundary markers: Absent; the instructions do not use delimiters or instructions to ignore embedded commands. 3. Capability inventory: None; the skill does not use scripts, subprocesses, or network commands. 4. Sanitization: Absent.
  • [No Code] (SAFE): This skill contains only natural language instructions and no executable scripts, binaries, or package dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 04:45 AM