the-signal-queue
Warn
Audited by Snyk on Aug 14, 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 skill’s runtime workflow ingests “This week’s signals” from the user and explicitly treats “fetched or pasted input” (including exports/transcripts/inbound replies) as untrusted data, which means the LLM can ingest outsider-authored free text whenever it’s pasted/imported into the signals batch.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata