meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted meeting transcripts. * Ingestion points: The agent is instructed to scan local folders for various transcript files (.txt, .md, .vtt, .srt, .docx). * Boundary markers: The instructions lack delimiters or specific guidance for the agent to ignore instructions embedded within transcript data. * Capability inventory: No dangerous capabilities such as network exfiltration, arbitrary command execution, or file system modifications are present. * Sanitization: There are no explicit steps for sanitizing or filtering transcript content.
  • [NO_CODE]: The skill is composed entirely of natural language instructions and does not include any executable scripts or automated installation procedures.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 10:06 PM