skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/voice-to-report/Snyk

voice-to-report

Warn

Audited by Snyk on Sep 18, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The workflow processes voice messages from chat/social feeds (Telegram) or user-provided audio files, which can contain outsider-authored spoken free text processed by speech-to-text and ingested into the LLM.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 18, 2026, 01:08 AM

Issues

1