meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and metadata contain no signs of obfuscation, malicious command execution, or unauthorized data exfiltration. The functionality is purely analytical and consistent with the stated purpose.
- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface as it processes external meeting transcripts. Analysis of the attack surface:
- Ingestion points: The skill scans and reads meeting transcripts in .txt, .md, .vtt, .srt, and .docx formats from user-specified folders.
- Boundary markers: Absent; the instructions do not explicitly provide delimiters to separate transcript content from agent instructions.
- Capability inventory: The skill has no capabilities for network access, file writing, or subprocess execution, meaning any potential injection could not result in data exfiltration or system compromise.
- Sanitization: No validation or sanitization of transcript content is performed. Given the lack of dangerous capabilities, this surface is considered a functional characteristic rather than a security risk.
Audit Metadata