The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as its primary purpose is to ingest and analyze external project files and infrastructure configurations.
Ingestion points: Local file paths provided as targets to scripts/pipeline_generator.py, scripts/terraform_scaffolder.py, and scripts/deployment_manager.py.
Boundary markers: There are no specific boundary markers or instructions to the agent to disregard embedded instructions within the ingested project data.
Capability inventory: The scripts in scripts/ have file-writing capabilities (via the --output flag). Additionally, the skill documentation in SKILL.md references the use of powerful tools such as docker, kubectl, and terraform.
Sanitization: The provided scripts do not implement sanitization or validation logic for the content of the files they are intended to analyze.
[COMMAND_EXECUTION]: The skill provides several Python scripts (scripts/pipeline_generator.py, scripts/terraform_scaffolder.py, scripts/deployment_manager.py) intended for local execution to perform DevOps automation. The SKILL.md file also explicitly mentions the use of common CLI tools and shell commands like docker build and kubectl apply for deployment and management tasks.

senior-devops