sentry-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and inspect user-generated/untrusted content from Sentry (e.g., "sentry issue view", "sentry event view", "sentry replay view", and "sentry api " in SKILL.md and the references), which the agent is expected to read and which can materially influence subsequent commands or decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The installation step includes a curl piped to bash that fetches and executes remote code from https://cli.sentry.dev/install, which is a runtime external fetch that executes remote code and is required for the CLI prerequisite.