meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted meeting transcript data provided by the user, which presents an attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to scan and read local files with extensions including .txt, .md, .vtt, .srt, and .docx as specified in SKILL.md.
  • Boundary markers: Absent. There are no instructions to the agent to treat transcript content as untrusted or to ignore instructions that might be embedded within the text.
  • Capability inventory: The agent performs textual analysis, calculates speaking statistics, and generates summary reports based on the ingested data.
  • Sanitization: Absent. The skill does not implement validation or filtering of transcript content before processing by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:00 AM