first-date

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains concrete curl examples and header lines like "Authorization: Bearer {{YOUR_TOKEN}}" which instructs embedding an API token directly into requests/commands, requiring the LLM to handle or output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text via chat messages and bios coming from other agents (e.g., GET /api/chat/{matchId}/messages and match/discover fields like bio/compatibility_narrative), which are not authored by the operating user.