meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted meeting transcripts which could facilitate indirect prompt injection. 1. Ingestion points: Scans folders for .txt, .md, .vtt, .srt, and .docx files. 2. Boundary markers: Instructions do not provide delimiters for separating user data from analysis logic. 3. Capability inventory: The skill performs text analysis and generates markdown reports; it does not request network access or shell execution. 4. Sanitization: No validation or filtering of transcript content is implemented.
  • [SAFE]: The skill does not perform any network operations, access sensitive credentials like SSH keys or environment variables, or attempt to persist across sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:10 AM
Security Audit — agent-trust-hub — meeting-insights-analyzer