meeting-intelligence-system

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): The skill is vulnerable to indirect prompt injection as it processes untrusted meeting data. * Ingestion points: User-provided meeting transcripts, notes, and recordings mentioned in SKILL.md. * Boundary markers: Absent; there are no instructions to delimit transcript content from agent instructions. * Capability inventory: Limited to text reasoning and generation; no high-risk capabilities like network or file access detected. * Sanitization: None provided for incoming text.
  • No Code (SAFE): No scripts, executables, or external packages were found; the skill relies entirely on prompt-based instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:51 PM