aio-telemetry-instrument
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation from the vendor's official repository and well-known industry standards to provide accurate instrumentation guidance.
- Evidence: References
https://raw.githubusercontent.com/adobe/aio-lib-telemetry/refs/heads/main/docs/for usage guides and API references. - Evidence: References
https://opentelemetry.io/docs/languages/js/for OpenTelemetry JS documentation. - [INDIRECT_PROMPT_INJECTION]: The skill processes external project files which could potentially contain malicious instructions intended to influence the agent's behavior during code analysis.
- Ingestion points: Reads
app.config.yaml,ext.config.yaml, and individual action source code files in the action's directory. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when reading these files.
- Capability inventory: The skill performs file reading, code analysis, and implements code changes such as function wrapping (
instrument) and metric definitions (defineMetrics). - Sanitization: No validation or sanitization of the input files is performed before processing.
Audit Metadata