techstack-identification

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

• Third-party content exposure detected (high risk: 0.90). The skill set clearly fetches and ingests untrusted public content — e.g., api_portal_discovery fetches OpenAPI specs and developer portals via WebFetch, certificate_transparency queries crt.sh, code_repository_intel scrapes public GitHub/GitLab repos, and domain_discovery uses web search/WebFetch — and those third‑party artifacts are parsed and used to drive inferences and downstream actions, which could allow indirect prompt injection.