The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for the agent to analyze and refactor source code fragments, creating a surface for potential injection if the code being analyzed contains malicious instructions.
Ingestion points: The workflow involves reading duplication reports and source code fragments from local files (SKILL.md, Workflow steps 2-4).
Boundary markers: The instructions do not specify the use of delimiters or specific system instructions to ignore embedded commands within the processed code.
Capability inventory: The agent is tasked with executing shell commands via npx jscpd and performing file system writes to apply refactoring changes (SKILL.md, Workflow steps 1 and 7).
Sanitization: No explicit sanitization or validation of the ingested source code content is described.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx jscpd to detect code clones. This tool is a well-known utility for this purpose and is authored by the skill's creator.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and run the jscpd package from the official npm registry. This represents standard usage of development tooling for the author's own utility.

dry-refactoring