meeting-intelligence-system

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to process external meeting transcripts which are untrusted data. * Ingestion points: User-provided meeting transcripts, recordings, or notes. * Boundary markers: Absent. The skill does not define delimiters to isolate untrusted data from the agent's instructions. * Capability inventory: None. The skill contains no code and performs no network or file operations. * Sanitization: Absent. There are no instructions to filter or escape potential malicious content within transcripts.
  • No Code (SAFE): The skill contains no scripts or external dependencies, which eliminates risks related to remote code execution, command injection, or malicious package installations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM