otelview-instrument
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install official OpenTelemetry packages using standard package managers (npm and pip). The packages identified, such as @opentelemetry/sdk-node and opentelemetry-distro, are industry-standard observability libraries and are considered safe.\n- [COMMAND_EXECUTION]: The skill includes benign shell commands for starting the local otelview tool and verifying the setup via curl. These commands are typical for development and diagnostics in this context.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes a process that enables an agent to ingest and process telemetry data from external applications. This creates a surface for indirect prompt injection if the ingested telemetry (logs or spans) contains instructions intended to influence the agent when it later uses analysis tools.\n
- Ingestion points: Application telemetry (traces, logs, metrics) sent to the otelview backend (SKILL.md).\n
- Boundary markers: No delimiters or explicit warnings to ignore embedded instructions are described in the setup guide.\n
- Capability inventory: The skill references capabilities for starting the service, persisting data to duckdb, and performing network verification via curl (SKILL.md).\n
- Sanitization: No evidence of data sanitization or validation is present in these instrumentation instructions.
Audit Metadata