agentlens-tracing-instrument
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided code files to add instrumentation. While this presents an inherent surface for indirect prompt injection, the skill includes instructions for content suppression and warns against recording sensitive information.
- [COMMAND_EXECUTION]: Instructions include running
wandb login --verifyto perform non-interactive identity checks. This is a standard procedure for verifying environment configuration before proceeding. - [EXTERNAL_DOWNLOADS]: The skill references the installation of official SDKs, specifically
coreweave-forge-sdkfor Python and@coreweave/forge-sdkfor Node.js. - [DATA_EXFILTRATION]: The skill facilitates the transmission of telemetry data to
trace.wandb.ai. This behavior is the intended purpose of the tracing skill and is performed using the vendor's official infrastructure.
Audit Metadata