sentry-otel-exporter-setup

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

• Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to fetch and use live content from public third-party sources (e.g., using the GitHub API to get releases and WebFetch to retrieve example configs from raw.githubusercontent.com) and explicitly requires the agent to read and incorporate that untrusted external config into the collector setup, which could materially influence subsequent tool use and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs fetching and running remote binaries/images at runtime—e.g., downloading the OpenTelemetry Collector tarball from https://github.com/open-telemetry/opentelemetry-collector-releases/releases/download/v<numeric_version>/otelcol-contrib_<numeric_version>.tar.gz and/or pulling the Docker image otel/opentelemetry-collector-contrib:<numeric_version>—which are required runtime dependencies that will execute remote code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt tells the agent to perform system actions (run curl/uname/tar/chmod, edit or create config and .env files, and run Docker containers) — explicitly asking the agent to execute changes on the host rather than only showing commands — so it instructs modifying the machine's state.