The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the ravi CLI tool for identity management, authentication flows, and credential retrieval.
[PROMPT_INJECTION]: Exhibits a surface for indirect prompt injection by processing untrusted data from external sources. Ingestion points: Reads SMS and email content via ravi inbox sms and ravi inbox email (SKILL.md). Boundary markers: Absent; the skill does not define specific delimiters or instructions for the agent to safely handle potentially malicious content within messages. Capability inventory: The skill has the ability to execute shell commands and interact with credential storage via the ravi CLI. Sanitization: Employs basic pattern matching via grep to extract OTPs and URLs, which provides limited filtering of the untrusted input.

ravi-login