The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides the agent with access to bash, git, and file system operations to perform infrastructure assessment, pipeline implementation, and deployment tasks.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external, potentially untrusted project data while possessing high-capability tool access.
Ingestion points: Analyzes project architecture, reviews application codebase, and reads system logs during the 'Infrastructure Assessment' phase (SKILL.md).
Boundary markers: Absent. There are no instructions or delimiters to help the agent distinguish between its system instructions and instructions found within project files.
Capability inventory: The agent has access to a shell (bash), version control (git), and file writing capabilities across the codebase (SKILL.md).
Sanitization: Absent. The skill does not define methods for filtering or escaping content read from the project environment.
[EXTERNAL_DOWNLOADS]: The CI/CD templates reference industry-standard external resources, such as GitHub Actions and the securecodewarrior/docker-security-scan Docker image for static security analysis.
[SAFE]: No hardcoded secrets, obfuscation, or unauthorized persistence mechanisms were identified. The skill promotes security best practices, including secrets management and automated vulnerability scanning.

devops