social-media
Warn
Audited by Snyk on Jul 4, 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 delegates “Research [TOPIC]” to a
researchersubagent and then reads a saved findings file (research/[slug].md); if that research fetches public web content at runtime, the LLM will ingest outsider-authored free text from those pages via the findings file.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata