openobserve
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to use
WebFetchto read documentation from the officialopenobserve.aiwebsite. - Ingestion points:
WebFetch("https://openobserve.ai/docs/quickstart/")inSKILL.md. - Boundary markers: Absent; instructions do not include specific delimiters or warnings for the fetched content.
- Capability inventory: The agent uses fetched data to provide code snippets, ingestion configurations, and deployment steps.
- Sanitization: None; content is fetched directly from the official source.
- [CREDENTIALS_UNSAFE]: The skill includes hardcoded example credentials (
root@example.com:Complexpass#123) withincurland Docker configuration examples. These are clearly used as illustrative placeholders for quickstart purposes and do not represent leaked production secrets. - [EXTERNAL_DOWNLOADS]: The skill references the official OpenObserve Docker image on the Amazon ECR public registry (
public.ecr.aws/zinclabs/openobserve). This is a documented, official distribution channel for the software and is considered a safe reference.
Audit Metadata