doc-coauthoring
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs the agent to fetch and read user-provided templates/links/files and “team channels or shared documents” via integrations during Stage 1, which can include outsider-authored free text once fetched/ingested into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata