meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or security risks were found in the skill's instructions or metadata. The skill's behavior is consistent with its stated purpose of behavioral analysis.
  • [NO_CODE]: The skill consists only of documentation and contains no scripts or executable code.
  • [PROMPT_INJECTION]: The skill ingests external data (meeting transcripts), which is a surface for indirect prompt injection. This is documented neutrally as it is the primary use case of the skill. 1. Ingestion points: Reads transcript files with extensions like .txt, .md, .vtt, .srt, and .docx from user-specified local folders. 2. Boundary markers: No specific delimiters are used to wrap the transcript content. 3. Capability inventory: Uses the agent's standard file-reading and analysis capabilities. 4. Sanitization: No sanitization of transcript content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 07:18 AM
Security Audit — agent-trust-hub — meeting-insights-analyzer