discord-clawd

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit patterns that read bot tokens (ssh printing $DISCORD_BOT_ID_FLAWD) and shows passing a DISCORD_BOT_TOKEN inline on the command line (DISCORD_BOT_TOKEN="..." /tmp/discrawl ...), which requires embedding secret values verbatim in commands/outputs.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and interprets user-generated Discord messages from the local archive (/.discrawl/discrawl.db) and can optionally live-refresh from the Discord repo (/Projects/discrawl), meaning untrusted social-media content is read as part of its workflow and could influence actions or decisions.