sentry-feature-setup

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs using curl at runtime to download SKILL.md files from https://skills.sentry.gg/sentry-setup-ai-monitoring/SKILL.md (and other paths under https://skills.sentry.gg/) whose contents the agent is told to "trust" and follow, so the fetched remote content would directly control agent instructions.