appinsights-instrumentation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill identifies a surface for indirect prompt injection because it analyzes local source code to determine the appropriate instrumentation logic. However, since this is the primary purpose of the skill and it involves standard developer operations using trusted libraries, the severity is downgraded to SAFE. Evidence: 1. Ingestion points: The skill reads workspace source code as defined in SKILL.md. 2. Boundary markers: No specific delimiters are mandated for the analysis of local code. 3. Capability inventory: Commands include 'az CLI' resource management and package installation ('npm', 'pip', 'dotnet'). 4. Sanitization: The skill relies on the agent's logic to interpret source files correctly.
Audit Metadata