The Agent Skills Directory

[SAFE]: The skill serves as a technical resource for CI/CD engineers, providing documentation and best practices for Woodpecker CI configuration.
[PROMPT_INJECTION]: The skill processes existing CI/CD configuration files to facilitate migration, which introduces a surface for indirect prompt injection from untrusted source repositories.
Ingestion points: The agent uses Read, Grep, and Glob tools to ingest content from existing pipeline files (e.g., in .github/workflows/ or .semaphore/).
Boundary markers: No explicit delimiters or instructions to ignore embedded prompts within the source files are defined.
Capability inventory: The skill employs Write, Edit, and Bash tools, enabling it to create new configuration files and execute shell commands.
Sanitization: No specific sanitization or validation of the input pipeline data is performed during the translation process.
Mitigation: It is recommended to review the generated Woodpecker configurations to ensure no malicious instructions from the source files were incorporated into the output.

writing-woodpecker-ci