meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the meeting transcripts it processes.
  • Ingestion points: The agent is instructed to scan and read files with various extensions (.txt, .md, .vtt, .srt, .docx) from the user's filesystem.
  • Boundary markers: The instructions lack delimiters or warnings to treat the transcript content as data rather than instructions, which could allow an attacker who controls a transcript file to influence the agent's output.
  • Capability inventory: The skill's capabilities are limited to reading local files and performing natural language analysis; no command execution or network access is requested.
  • Sanitization: There is no evidence of sanitization or filtering of the content read from the files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:30 PM