Meeting Intelligence Query

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted meeting transcripts which could contain malicious instructions.\n
  • Ingestion points: Meeting transcripts are retrieved and processed through the meeting_intelligence_query and meeting_analytics_insights actions defined in SKILL.md.\n
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or to disregard instructions found within the transcript text.\n
  • Capability inventory: The skill has the ability to trigger multiple analytical tools and potentially hand off to a task creation system, providing a path for injected instructions to affect external state.\n
  • Sanitization: The skill does not implement any sanitization or validation logic to filter out potential command-like structures from the transcript data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM