github-issue-rca

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly requires fetching and analyzing public third-party content—e.g., Step 2 "Search and Analyze Similar Issues" using github_search_issues and Step 4 "External Context Investigation" (web search / Stack Overflow / blog posts)—and mandates using those findings to form hypotheses and drive actions, so untrusted external content can influence agent behavior.