The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from the repository (sonar-project.properties) and user-provided command-line arguments (e.g., project keys, file paths, and PR IDs).
Ingestion points: The skill reads the sonar-project.properties file in Step 1 and parses user-supplied flags in Step 2.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the interpolated data.
Capability inventory: The skill possesses the capability to read files (Read, Grep) and execute shell commands (Bash(sonar:*), Bash(docker ps:*), etc.) as well as call specialized MCP tools.
Sanitization: No explicit sanitization or validation logic is provided for the interpolated variables.
[COMMAND_EXECUTION]: The skill instructs the agent to construct shell commands for the sonar CLI fallback (Flow A and B) using variables derived from external input. If these variables contain shell metacharacters and the execution environment does not properly escape them, it could lead to command injection within the scope of the sonar command.

sonar-coverage