lint
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands including
dotnet build,nx lint, andnpx prettierto analyze and format code. These are common development operations within a local environment and are restricted to the task's scope. - [PROMPT_INJECTION]: The skill ingests and processes untrusted data from the local codebase to identify code patterns and apply linting rules. While this creates a surface for indirect prompt injection, it is a necessary part of the skill's function.
- Ingestion points: Source code files in the repository and local protocol files such as
.claude/skills/shared/understand-code-first-protocol.md. - Boundary markers: None explicitly implemented to separate external content from instructions.
- Capability inventory: Read access to the local file system and shell command execution using standard build and linting binaries.
- Sanitization: The skill does not perform explicit sanitization of the code content it processes.
Audit Metadata