security-headers-check

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow uses curl to fetch the target site’s HTTP response headers from a user-supplied URL/domain (curl -sIL ... and curl -sI ... "$FINAL"), and those headers are then ingested as readable text into the agent context via /tmp/headers.txt and the subsequent grep/reporting—this is outsider-authored free text from an arbitrary external web server.