meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests external meeting transcripts, creating a vulnerability surface where instructions embedded in those transcripts could influence agent behavior.
  • Ingestion points: The skill reads .txt, .md, .vtt, .srt, and .docx files from local directories such as ~/meetings/ as specified in SKILL.md.
  • Boundary markers: There are no instructions provided to the agent to use XML tags, delimiters, or specific 'ignore' directives to separate the transcript content from the analysis instructions.
  • Capability inventory: The skill is restricted to file reading and text analysis within the SKILL.md workflow. It does not utilize shell execution, network tools, or other high-privilege capabilities.
  • Sanitization: The skill does not define any methods for validating or sanitizing the content of the transcript files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:08 PM
Security Audit — agent-trust-hub — meeting-insights-analyzer