weekly-intel-digest

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly searches and reads user-generated messages from public/private Slack channels (e.g., #feed-swyft-meetings, #feed-competitor-feedback, #feed-twitter) via slack_search_public_and_private and ingests those DM/thread responses into its analysis and report, meaning untrusted third-party content can influence tool use and next actions.