ravi-login

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to retrieve plaintext credentials and OTPs (via ravi passwords get, ravi passwords create, ravi inbox sms/email) and then "use" those values directly in signup forms and logins, which requires the LLM/agent to handle and output secret values verbatim.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses external messages using "ravi inbox sms" and "ravi inbox email" (see "Complete 2FA / OTP" and "Extract a verification link from email") to extract OTPs/verification links which the agent then acts on, exposing it to untrusted third-party content that could inject instructions.