tech-article-reproducibility
Warn
Audited by Snyk on Apr 28, 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's subagent dispatch template in SKILL.md explicitly instructs the evaluator to check "Link health (actually verify with WebFetch)" (axis 9), which requires fetching and reading public third-party web pages and using those results to score/reason about reproducibility, so untrusted external content can influence the agent's decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata