slate-plan

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

• Third-party content exposure detected (high risk: 0.75). At runtime, this skill reads multiple ledger files that are generated from live gitcrawl/GitHub data (e.g., docs/slate-issues/gitcrawl-live-open-ledger.md and related sync/fork dossier inputs), which can contain outsider-authored issue/comment text that the agent then incorporates into its LLM context via those markdown files.