The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes project configuration files to automate linter setup, creating a surface where malicious project content could influence agent actions.
Ingestion points: The script scripts/inspect-project.py reads build.gradle, build.gradle.kts, settings.gradle, settings.gradle.kts, and libs.versions.toml from the target project.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the inspection logic.
Capability inventory: The results from the file inspection are used to drive command execution via the Gradle wrapper (./gradlew), involving configuration generation and analysis tasks.
Sanitization: The process relies on regular expressions for data extraction but does not sanitize the input files for potential injection patterns.

detekt