lead-research
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This skill’s workflow explicitly includes “Read what they publish” (e.g., engineering blog/job postings/changelog) and “Find the trigger” from public artifacts, which at runtime would require fetching outsider-authored web text and ingesting it into the LLM context for summarization/quoting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata