sdk-adoption-tracker

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public, user-generated GitHub content (see SKILL.md Step 3 "Search GitHub Code" and Step 5 "Enrich High-Signal Repos" which call the GitHub code search and /repos, /users, /orgs, /contributors APIs) and then the agent reads those repo files/descriptions/owner profiles to compute scores and generate outreach briefs, so untrusted third-party content can directly influence decisions and outputs.