ci-test-failures
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill facilitates the execution of local .NET projects and GitHub CLI commands. These operations are intended for interacting with the repository's CI system and managing issues, which are appropriate for a developer-oriented diagnostic skill.
- Dynamic Execution: The skill involves compiling and running C# scripts and .NET tools at runtime. This behavior is a standard approach for diagnostic tooling provided within a repository and is used here to download logs and process test artifacts.
- Indirect Prompt Injection Surface: The agent is instructed to analyze external data such as CI logs and test results. While these files are processed at runtime, the skill provides specific search patterns and structured tools like
jqandSelect-Stringto handle the data, which minimizes the risk of the agent misinterpreting the content as instructions. - Trusted Infrastructure Interaction: All network activities, including downloading artifacts and API calls, are directed toward official GitHub domains for the purpose of maintaining a repository authored by a known organization. This alignment with intended functionality is considered safe.
Audit Metadata