dotnet-cli-fix-loop
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
dotnet buildanddotnet runto compile and execute local code. This is the primary intended purpose of the skill and is restricted to the specific CLI tools in the allowed-tools configuration. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from build logs and source code.
- Ingestion points: Reads source code files and the stdout/stderr output from
dotnet buildanddotnet runas described in SKILL.md. - Boundary markers: None. The skill does not use specific delimiters or instructions to ignore potential commands embedded in the project files or error messages.
- Capability inventory: The agent can execute
Bashcommands (build and run) and write code changes to the filesystem. - Sanitization: No sanitization of project content or tool output is performed before processing.
Audit Metadata