marketplace-health-check

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses gh pr list/gh issue list and then gh pr view / gh issue view to read PR/issue bodies authored by external contributors, which are free-form text that the workflow agents ingest into the LLM context (outsider-authored content via GitHub APIs).

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)