The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill provides an attack surface for indirect injection by processing untrusted user tasks while possessing high-privilege tool access.
Ingestion points: User tasks passed via prompt or CLI mentioned in references/GUIDE.md (e.g., `claude "java-spring-boot
[your task description]"`).
Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded commands are defined in the sample prompts.
Capability inventory: The skill is granted Bash and Write permissions in SKILL.md, allowing it to create files and execute commands.
Sanitization: No explicit sanitization or input validation of the natural language task description is implemented before it influences tool usage.
[Unverifiable Dependencies] (SAFE): The scripts/validate.py script uses standard libraries and PyYAML. No remote code execution or piped bash scripts from external URLs were detected.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network calls were found. The skill configuration uses placeholders and environment variables.
[Obfuscation] (SAFE): No evidence of Base64 encoding, zero-width characters, or homoglyph-based evasion was found in any of the files.

java-spring-boot