transcript-search

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process external meeting transcript data.
  • Ingestion points: Transcripts are retrieved via GraphQL API in 'scripts/fireflies_transcript_search.py' and from Google Drive files in 'scripts/gdrive_transcript_search.py'.
  • Boundary markers: The scripts do not implement specific delimiters or instructions to ignore embedded commands within the transcript content.
  • Capability inventory: The skill has the capability to write files to the local '.tmp' directory and specified output paths, and it performs network operations to established service endpoints.
  • Sanitization: Transcript data is processed and stored as raw text without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 04:23 AM