open-observe-api-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- Data Exposure & Exfiltration (LOW): The skill facilitates network requests to api.openobserve.ai. While this domain is not on the pre-approved whitelist, the activity is central to the skill's purpose as an observability tool. No access to sensitive local configuration files was detected.
- Indirect Prompt Injection (LOW): The skill defines an interface for processing external log data and executing search queries, which are untrusted inputs.
- Ingestion points: Untrusted data enters the agent context via the 'logs' parameter in 'send_logs' and via results from 'search_logs'.
- Boundary markers: Documentation lacks guidance on using delimiters (like triple backticks or XML tags) or system instructions to ignore embedded commands within the log data.
- Capability inventory: The skill facilitates network communication with the OpenObserve API to both send data and retrieve logs.
- Sanitization: No explicit sanitization or validation of the log content is demonstrated in the integration examples.
Audit Metadata