meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingest and processes untrusted meeting transcripts that could contain hidden instructions.
  • Ingestion points: Reads local transcript files in formats such as .txt, .md, .vtt, .srt, and .docx from user-specified directories (e.g., ~/meetings/).
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to treat the transcript content strictly as data.
  • Capability inventory: The skill's instructions are limited to reading files and providing textual analysis. It does not define capabilities for writing files, executing system commands, or performing network operations.
  • Sanitization: There is no explicit logic provided to sanitize or escape malicious strings within the processed transcripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — meeting-insights-analyzer