meeting-intelligence-system

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process meeting transcripts provided by the user, which constitutes a surface for indirect instructions.
  • Ingestion points: Meeting transcripts, recordings, and notes provided in the user's prompt (SKILL.md).
  • Boundary markers: The instructions do not define delimiters (e.g., xml tags or markers) to separate user data from instructions, nor do they instruct the agent to ignore instructions embedded in the transcript.
  • Capability inventory: The skill is restricted to text analysis and generation; it has no access to shell execution, network tools, or file-writing capabilities.
  • Sanitization: There is no evidence of input validation or content sanitization for the transcript data.
  • [NO_CODE]: The skill consists entirely of markdown instructions and templates, with no scripts, binaries, or library dependencies included.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — meeting-intelligence-system