opentelemetry
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong imperative language, including "CRITICAL" and "MUST", to override the agent's internal knowledge and mandate the use of the
WebFetchtool before proceeding. - [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by requiring the agent to ingest data from an external website. While the target is a reputable official site, the pattern of processing untrusted content into the prompt context is a known vulnerability.
- Ingestion points: Fetches content from
https://opentelemetry.io/docs/languages/js/as directed inSKILL.md. - Boundary markers: None provided; the agent is not instructed to ignore embedded directives in the fetched content.
- Capability inventory: The skill provides instructions for Node.js execution, instrumentation, and resource detection, which involve shell command execution and environment configuration.
- Sanitization: No validation or sanitization is performed on the fetched documentation content.
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation from OpenTelemetry's official website. This is an established and reputable service used to ensure the accuracy of the agent's responses.
Audit Metadata