html-research-reports
Warn
Audited by Snyk on Jul 7, 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). SKILL.md:21-22 and SKILL.md:77-78 describe synthesizing from runtime-accessed sources like “threads” and “web” (public web content / outsider-authored messages), which would be ingested as readable text into the agent’s LLM context to produce the HTML report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata