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-frontmattercommand. 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