The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite external text such as messages, pull request descriptions, and documents. This creates a surface where instructions embedded in the input text could potentially influence the agent's behavior during the transformation process.
Ingestion points: Processes user-provided drafts, messages, and documents as specified in the "Triggers on" and "Applies to" sections of SKILL.md.
Boundary markers: No specific delimiters or "ignore" instructions are defined for the input text to prevent the agent from following instructions contained within the data being processed.
Capability inventory: Mentions the execution of a project-specific CLI tool, agentic-sdlc.
Sanitization: The instructions do not specify any sanitization, escaping, or filtering of the external content before processing.
[COMMAND_EXECUTION]: The skill instructions and documentation describe the use of the agentic-sdlc lint-voice command-line tool to perform mechanical style checks on repository files.

plain-voice