spec-loop-assess-pull-request

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and ingest untrusted, user-generated provider content (PR/MR pages, diffs, commit messages, and discussion comments) via gh/glab as required evidence (see SKILL.md and review-guidance.md), which the agent will read and use to form assessments and next actions, exposing it to indirect prompt-injection risk.