The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting and analyzing untrusted data from local project files and external documentation sources while maintaining high-privilege capabilities.
Ingestion points: The skill reads tsconfig.json, TypeScript source files, and fetches documentation from an external source via mcp__plugin_claude-code-home-manager_context7__query-docs.
Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores or sanitizes instructions embedded within the data it processes.
Capability inventory: The skill utilizes Bash (arbitrary shell access), Edit (filesystem write), and Read (filesystem read) tools.
Sanitization: None. The skill does not specify any validation or escaping mechanisms for the content it retrieves before using it to inform code changes or command execution.
[COMMAND_EXECUTION]: The skill provides instructions and examples for executing shell commands via the Bash tool, including compiler operations (tsc), runtime execution (node, tsx), and package management (npm). While these commands are standard for the described purpose, their execution in the context of potentially compromised project data presents a risk of command injection or malicious code execution if the agent follows instructions found within the analyzed files.

TypeScript Ecosystem