meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from meeting transcripts which could contain hidden malicious instructions.
  • Ingestion points: The skill instructions the agent to scan and read transcript files in formats including .txt, .md, .vtt, .srt, and .docx from user-provided local folders (SKILL.md).
  • Boundary markers: Absent. No specific delimiters or instructions to ignore embedded commands are provided to separate data from the analysis logic.
  • Capability inventory: No subprocess calls, file-write operations, or network requests are defined in the skill itself (SKILL.md).
  • Sanitization: Absent. There are no requirements or methods specified for validating or filtering the content of the meeting transcripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:21 PM
Security Audit — agent-trust-hub — meeting-insights-analyzer