The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to run npx react-doctor@latest. This command downloads and executes code from the public NPM registry at runtime. The use of the @latest tag means the code being executed is not pinned to a specific version, which could allow for the execution of compromised code if the package is hijacked.
[COMMAND_EXECUTION]: The skill uses npx to execute shell commands on the local system to perform codebase scans. This grants the external package the ability to execute instructions in the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes local React codebases, which are external data sources that could potentially contain malicious instructions designed to manipulate the agent's summary or health score evaluation.
Ingestion points: Local codebase files scanned via the react-doctor CLI (SKILL.md).
Boundary markers: None mentioned; the tool analyzes code files directly.
Capability inventory: Shell command execution via npx (SKILL.md).
Sanitization: No sanitization or input validation is described for the files processed by the tool.

react-doctor