fluentbit-validator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md Stage 8 ("Documentation Lookup") explicitly instructs the agent to fetch documentation via context7 and fallback to WebSearch (e.g., site:docs.fluentbit.io and arbitrary web queries) and to "Extract information" from those public sites, meaning the agent will read and act on untrusted third‑party web content to influence validation and fixes.