paw-pa-library

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from the runtime directory library/inbox/** is read as UTF-8 (scripts/ingest-library.py:526-527), then included verbatim into generated index/markdown outputs (case-studies-index.json, pricing-history.json, scope-templates.md, and brand/boilerplate/*.md) which are then passed along to downstream agent skills as context; there is no LLM-only filtering/sanitization in this workflow.