agent-instagram

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask for usernames/passwords and to run non-interactive commands that embed passwords (e.g., --password "mypassword") and also describes extracting session cookies, which forces inclusion or handling of secret values verbatim in commands/output.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses Instagram user-generated content (chat list, message list, message search) via HTTP calls to Instagram in SKILL.md and the accompanying scripts (e.g., agent-instagram chat list / message list and the monitor/post scripts), so the agent will read untrusted third-party DM text that can influence its decisions or subsequent tool use.