The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run environment checks and analysis commands. This includes git branch for branch detection, docker ps, podman ps, and nerdctl ps for container runtime verification, and the sonar CLI for Vortex analysis. These executions are scoped to specific functionality and are standard for developer tools.
[INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of source files for analysis, creating a vulnerability surface where malicious code could influence the agent's behavior during the analysis process.
Ingestion points: Full file content is read via the Read tool as described in Step 2 and Step 3 of the instructions.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the analyzed file content.
Capability inventory: The skill has access to file system tools (Read, Glob) and command execution tools (Bash for git, docker, and sonar).
Sanitization: There is no evidence of content sanitization, escaping, or filtering before the file content is passed to the analysis tools.

sonar-analyze