agent-discordbot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit CLI examples that pass bot tokens as direct command-line arguments (e.g., agent-discordbot auth set <token> / auth set your-bot-token), which encourages the LLM/agent to accept and embed secret values verbatim in generated commands or outputs.

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 interprets Discord user-generated messages (untrusted third-party content) — e.g., SKILL.md's snapshot/message list output includes recent message content and templates/monitor-channel.sh and references/common-patterns.md (Pattern 3) show polling a channel and taking actions based on message text — so external messages can influence agent decisions.