vault-closeday

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

• Third-party content exposure detected (high risk: 0.70). The skill's Workflow step 1 ("Pull today's GitHub commits") explicitly runs the gh api commands in SKILL.md to fetch commit messages from GitHub — user-generated, third-party content that the agent reads, summarizes, and merges into its daily-note workflow, so those external messages could influence its categorization and next actions.