process-meeting-transcript

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process raw meeting transcripts, which are untrusted external data sources that may contain embedded instructions intended to hijack the AI's behavior.
  • Ingestion points: Reads raw meeting transcripts from user input or files (Step 1 in SKILL.md).
  • Boundary markers: Absent. The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or explicit instructions for the AI to ignore commands found within the transcript text.
  • Capability inventory: The skill is limited to text summarization, formatting, and calling the internal add-frontmatter command. It lacks dangerous capabilities such as arbitrary command execution, network access, or sensitive file writing.
  • Sanitization: Absent. There is no evidence of content filtering, escaping, or validation of the transcript data before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM