nlp-earnings-sentiment
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow ingests the earnings-call transcript text (e.g., “Operator/CEO/CFO/Analyst” lines) into the LLM context; if that transcript is sourced from outsiders (public filings/web transcripts or other parties’ authored content), it becomes outsider-authored free text that can carry indirect prompt-injection payloads.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata