The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze and refactor external codebases, which exposes the agent to potential indirect prompt injection attacks.
Ingestion points: The skill ingests untrusted data from user-specified files and modules during refactoring workflows (documented in SKILL.md).
Boundary markers: There are no specific instructions or delimiters defined to prevent the agent from following malicious instructions hidden in code comments or data within the files being processed.
Capability inventory: The skill has access to file system operations (Read, Write, Grep, Glob) and restricted shell execution (Bash for npm test:* and npx:*) as specified in the SKILL.md frontmatter.
Sanitization: The instructions do not define any sanitization or validation logic to filter potentially harmful content from the source files before processing.
[COMMAND_EXECUTION]: The skill configuration allows for shell command execution restricted to test runners and npx utilities. While these are limited to specific patterns, they provide the agent with the ability to execute code in the local environment to verify refactoring results.

refactor