The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell scripts to invoke the mvn CLI for project discovery and analysis (e.g., mvn dependency:tree, mvn help:effective-pom). These commands are standard for Maven lifecycle management and are consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes external data from local files (like pom.xml) and the output of Maven plugins.
Ingestion points: Reads pom.xml via grep and processes output from various mvn help and mvn dependency goals.
Boundary markers: None identified; instructions do not explicitly tell the agent to ignore instructions embedded in the project files.
Capability inventory: The skill has the ability to execute shell commands and read files in the project directory.
Sanitization: No sanitization or escaping of the project-provided data is performed before it is processed or displayed.
[DATA_EXPOSURE]: The skill executes mvn help:effective-settings which outputs the merged Maven configuration. This may include server and mirror configurations. While this is a standard administrative task for Maven, it involves viewing sensitive infrastructure configuration.

managing-maven