The Agent Skills Directory

[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by ingesting and processing external data from SonarQube API outputs.
Ingestion points: External data enters the agent context through the results of mcp__sonarqube__search_duplicated_files, mcp__sonarqube__get_duplications, and sonar api commands as described in SKILL.md.
Boundary markers: The instructions do not mandate the use of delimiters or specific warnings to ignore embedded instructions within the ingested data.
Capability inventory: The skill has access to shell command execution through the Bash tool for the sonar CLI and container runtimes (docker, podman, nerdctl) defined in the frontmatter.
Sanitization: No explicit sanitization or content validation of the API-returned data is performed by the skill before processing or display.
[COMMAND_EXECUTION]: The skill uses Bash to execute commands for checking container runtime status and interacting with the SonarQube API. These capabilities are constrained to the specific tools allowed in the frontmatter configuration.
[EXTERNAL_DOWNLOADS]: The skill references the sonar-integrate skill, which is intended to manage the installation and configuration of the sonarqube-cli. This represents a standard setup workflow for tools provided by this vendor.

sonar-duplication