The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes local project source code and configuration files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Project source files in the src/ directory and git diff output.
Boundary markers: None specified to differentiate between instructions and project data.
Capability inventory: Shell execution via mvn, gradlew, grep, and git commands.
Sanitization: No sanitization is performed on the ingested file content.
[EXTERNAL_DOWNLOADS]: The skill invokes Maven to run security scans.
Evidence: Uses org.owasp:dependency-check-maven for CVE analysis, which involves downloading the plugin and vulnerability data from official OWASP sources.

springboot-verification