cody-article-writer
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly performs WebSearch and WebFetch on public URLs (see "Exploratory research" and Research Planning / Point 3 in references/research-workflow.md and the Article Workflow), caches excerpts into approved_sources via WebFetch, and then uses those untrusted, user/public web contents to shape the thesis, outline, writing, citations, and export decisions—allowing third-party content to materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata