meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted meeting transcripts that could contain malicious instructions embedded within the dialogue.
  • Ingestion points: Scans and reads various file formats (.txt, .md, .vtt, .srt, .docx) from local directories.
  • Boundary markers: None identified. The instructions do not direct the agent to use delimiters or a "data-only" mode when processing the content of the transcripts.
  • Capability inventory: The skill performs local file-read operations and sophisticated natural language processing on the ingested data.
  • Sanitization: None. The agent is instructed to find and quote actual snippets from the transcripts without prior sanitization or instruction-filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:33 PM
Security Audit — agent-trust-hub — meeting-insights-analyzer