kill-ai-slop

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow, the scanner (scripts/scan.mjs) reads and greps the user-provided project source tree from a local root directory (including .md/.mdx content) and produces LLM-relevant extracted free text (“file:line” snippets), so an outsider can supply those files by submitting/committing/creating the project content that the workflow scans.