application-inspector

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official security tools and references trusted documentation.
  • Fetches the Microsoft.CST.ApplicationInspector.CLI tool through the standard .NET tool manager.
  • Downloads the official app-inspector container image from the Microsoft Container Registry (mcr.microsoft.com).
  • Points to the official Microsoft GitHub organization for source code, documentation, and default rule sets.
  • Recommends the installation of the sarif-tools package from the Python Package Index for report filtering.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for analyzing external source code, creating a surface for indirect prompt injection if the code contains malicious patterns designed to influence the agent's interpretation of findings.
  • Ingestion points: Local source code directories analyzed using the -s or --source-code flags.
  • Boundary markers: The skill does not explicitly define delimiters for the tool's output when processed by the agent.
  • Capability inventory: The agent uses Bash to execute the analysis and Read/Grep tools to inspect the resulting SARIF, JSON, or HTML reports.
  • Sanitization: No specific filtering or sanitization steps are defined for the content extracted by the inspector tool before the agent reviews it.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 05:06 AM