kiterunner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows and documents passing bearer tokens directly on the command line (e.g., -A "bearer:TOKEN" and -A "bearer:$TOKEN"), which requires embedding secret values verbatim in generated commands/outputs.

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md shows it actively scans and replays arbitrary external targets (e.g., "kr scan https://target.com -w routes-small.kite" and "kr replay ... https://api.target.com/..."), meaning the agent fetches and interprets untrusted responses from public third-party servers as part of its workflow.