opentelemetry
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements observability patterns that ingest data from Telegram interactions, such as chat IDs, user IDs, command strings, and callback data, which are then recorded as trace attributes or sent to error reporting services.\n
- Ingestion points: The skill captures interaction data in
handleCommand,sendMessage,handleCallback, andhandleBotExceptionwithinSKILL.md.\n - Boundary markers: No delimiters or explicit warnings are used to distinguish or isolate the untrusted external data within the telemetry context.\n
- Capability inventory: The skill enables the agent to record telemetry data and exceptions using the OpenTelemetry API and Sentry SDK, which export data to external collectors and services.\n
- Sanitization: No sanitization or filtering of the external message content is performed before it is added to the telemetry attributes.
Audit Metadata